diff --git a/openpilot/sunnypilot/modeld_v2/__init__.py b/openpilot/sunnypilot/modeld_v2/__init__.py
index 639622e827..e69de29bb2 100644
--- a/openpilot/sunnypilot/modeld_v2/__init__.py
+++ b/openpilot/sunnypilot/modeld_v2/__init__.py
@@ -1,5 +0,0 @@
-from pathlib import Path
-
-MODEL_PATH = Path(__file__).parent / 'models/supercombo.onnx'
-MODEL_PKL_PATH = Path(__file__).parent / 'models/supercombo_tinygrad.pkl'
-METADATA_PATH = Path(__file__).parent / 'models/supercombo_metadata.pkl'
diff --git a/openpilot/sunnypilot/modeld_v2/compile_modeld.py b/openpilot/sunnypilot/modeld_v2/compile_modeld.py
index a274097563..1e88769928 100755
--- a/openpilot/sunnypilot/modeld_v2/compile_modeld.py
+++ b/openpilot/sunnypilot/modeld_v2/compile_modeld.py
@@ -32,7 +32,7 @@ def _patch_tinygrad_fetch_fw():
   helpers.fetch_fw = fetch_fw
 _patch_tinygrad_fetch_fw()
 
-from openpilot.selfdrive.modeld.compile_modeld import NV12Frame, make_frame_prepare, sample_desire, sample_skip, shift_and_sample
+import openpilot.selfdrive.modeld.compile_modeld as stock
 from tinygrad import dtypes
 from tinygrad.device import Device
 from tinygrad.engine.jit import TinyJit
@@ -41,7 +41,7 @@ from tinygrad.tensor import Tensor
 MODEL_TYPES = ('vision_policy', 'supercombo', 'vision_multi_policy')
 WARP_INPUTS = ['tfm', 'big_tfm']
 POLICY_INPUTS = ['img_q', 'big_img_q', 'feat_q', 'desire_q', 'packed_npy_inputs']
-
+nv12_copy_size = stock.nv12_copy_size
 
 def _detect_desire_key(shapes: dict) -> str | None:
   return next((key for key in shapes if key.startswith('desire')), None)
@@ -138,7 +138,7 @@ def make_supercombo_input_queues(input_shapes: dict, frame_skip: int,
   return generate_queues_and_npy(input_shapes, frame_skip, device, is_supercombo=True)
 
 
-def make_random_images(keys, shape, device):
+def make_random_images(keys, shape, device, rng=None):
   return {k: Tensor.randint(shape, low=0, high=256, dtype=dtypes.uint8, device=device).realize() for k in keys}
 
 
@@ -151,25 +151,9 @@ def make_warp_queues(device=Device.DEFAULT):
   return queues, npy
 
 
-def make_warp(nv12: NV12Frame, model_w: int, model_h: int):
-  frame_prepare = make_frame_prepare(nv12, model_w, model_h)
-
-  def warp(tfm, big_tfm, frame, big_frame):
-    tfm = tfm.to(Device.DEFAULT)
-    big_tfm = big_tfm.to(Device.DEFAULT)
-    frame = frame.to(Device.DEFAULT)
-    big_frame = big_frame.to(Device.DEFAULT)
-    Tensor.realize(tfm, big_tfm, frame, big_frame)
-
-    warped_frame = frame_prepare(frame, tfm).unsqueeze(0)
-    warped_big_frame = frame_prepare(big_frame, big_tfm).unsqueeze(0)
-    return Tensor.cat(warped_frame, warped_big_frame)
-  return warp
-
-
 def make_run_policy(vision_runner, policy_runners: list, features_slice: slice, frame_skip: int, input_shapes: dict):
-  sample_skip_fn = partial(sample_skip, frame_skip=frame_skip)
-  sample_desire_fn = partial(sample_desire, frame_skip=frame_skip)
+  sample_skip_fn = partial(stock.sample_skip, frame_skip=frame_skip)
+  sample_desire_fn = partial(stock.sample_desire, frame_skip=frame_skip)
 
   desire_key = _detect_desire_key(input_shapes)
   road_key, wide_key = _detect_vision_keys(input_shapes)
@@ -186,14 +170,14 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
     warped_dev = warped.to(Device.DEFAULT)
     Tensor.realize(packed_npy_inputs_dev, warped_dev)
 
-    img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
-    big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
+    img = stock.shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
+    big_img = stock.shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
 
     unpacked_tensors = [tensor.reshape(shape) for tensor, shape in zip(packed_npy_inputs_dev.split(npy_sizes), npy_shapes.values(), strict=True)]
     unpacked_dict = dict(zip(npy_shapes.keys(), unpacked_tensors, strict=True))
 
     desire_dev = unpacked_dict['desire']
-    desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
+    desire_buf = stock.shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
 
     inputs = {desire_key: desire_buf}
     for key, tensor_val in unpacked_dict.items():
@@ -202,13 +186,13 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
 
     if 'prev_feat' in unpacked_dict:
       prev_feat_dev = unpacked_dict['prev_feat']
-      inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
+      inputs['features_buffer'] = stock.shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
 
     if vision_runner:
       vision_out_cast = next(iter(vision_runner({road_key: img, wide_key: big_img}).values())).cast('float32').realize()
       if 'features_buffer' not in inputs:
         new_feat = vision_out_cast[:, features_slice].reshape(1, -1).unsqueeze(0)
-        inputs['features_buffer'] = shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
+        inputs['features_buffer'] = stock.shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
       policy_outs = [next(iter(pol_runner(inputs).values())).cast('float32').realize() for pol_runner in policy_runners]
       return (vision_out_cast, *policy_outs) if len(policy_outs) > 1 else (vision_out_cast, policy_outs[0])
 
@@ -219,27 +203,28 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
     policy_out = next(iter(policy_runners[0](inputs).values())).cast('float32').realize()
     if 'features_buffer' not in inputs and features_slice is not None:
       new_feat = policy_out[:, features_slice].reshape(1, -1).unsqueeze(0)
-      shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
+      stock.shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
     return policy_out
 
   return run_policy
 
 
-def compile_jit(jit, make_random_inputs, input_keys, make_queues):
+def compile_jit(jit, input_keys, make_queues, make_random_inputs=None, benchmark_runs: int = 1):
   SEED = 42
-  def random_inputs_run(fn, seed, test_val=None, test_buffers=None, expect_match=True):
-    input_queues, npy = make_queues(Device.DEFAULT)
+  def random_inputs_run(fn, seed, n_runs, test_val=None, test_buffers=None, expect_match=True):
+    queues_res = make_queues(Device.DEFAULT)
+    input_queues, npy = queues_res[0], queues_res[1]
+    frame_views = queues_res[2] if len(queues_res) > 2 else {}
     rng = np.random.default_rng(seed)
     Tensor.manual_seed(seed)
 
-    testing = test_val is not None or test_buffers is not None
-    n_runs = 1 if testing else 3
-
     for i in range(n_runs):
       for v in npy.values():
         v[:] = rng.standard_normal(v.shape).astype(v.dtype)
+      for v in frame_views.values():
+        v[:] = rng.integers(0, 256, size=v.shape, dtype=np.uint8)
       Device.default.synchronize()
-      random_inputs = make_random_inputs()
+      random_inputs = make_random_inputs(rng=rng) if make_random_inputs is not None else {}
       st = time.perf_counter()
       outs = fn(**{k: input_queues[k] for k in input_keys if k in input_queues}, **random_inputs)
       mt = time.perf_counter()
@@ -260,14 +245,15 @@ def compile_jit(jit, make_random_inputs, input_keys, make_queues):
     return val, buffers
 
   print('capture + replay')
-  test_val, test_buffers = random_inputs_run(jit, SEED)
-  print('pickle round trip')
+  test_val, test_buffers = random_inputs_run(jit, SEED, 3)
+  print(f'pickle round trip ({benchmark_runs} runs per seed)')
   with tempfile.TemporaryFile(dir=".") as f:
     dump_oob(jit, f)
     f.seek(0)
-    deserialized_jit = load_oob(f)
-  random_inputs_run(deserialized_jit, SEED, test_val=test_val, test_buffers=test_buffers)
-  return deserialized_jit
+    loaded_jit = load_oob(f)
+  random_inputs_run(loaded_jit, SEED, benchmark_runs, test_val, test_buffers, expect_match=True)
+  random_inputs_run(loaded_jit, SEED+1, benchmark_runs, test_val, test_buffers, expect_match=False)
+  return jit
 
 
 def _parse_size(size_str: str) -> tuple[int, int]:
@@ -317,6 +303,7 @@ if __name__ == "__main__":
   parser.add_argument('--model-size', type=_parse_size, required=True, help='model input WxH')
   parser.add_argument('--camera-resolutions', type=_parse_size, nargs='+', required=True)
   parser.add_argument('--frame-skip', type=int, default=None, help='frame skip value (auto-derived if not provided)')
+  parser.add_argument('--benchmark-runs', type=int, default=1, help='benchmark runs')
   parser.add_argument('--output', required=True)
 
   parser.add_argument('--vision-onnx', help='vision ONNX (for split models)')
@@ -335,50 +322,64 @@ if __name__ == "__main__":
   args.on_policy_onnx = read_file_chunked_to_disk(args.on_policy_onnx)
   args.supercombo_onnx = read_file_chunked_to_disk(args.supercombo_onnx)
 
-  vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None
-
-  if args.model_type == 'vision_policy':
-    assert vision_runner and args.policy_onnx
-    policy_runners = [OnnxRunner(args.policy_onnx)]
-    output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx), 'policy': make_metadata_dict(args.policy_onnx)}
-  elif args.model_type == 'supercombo':
+  if args.model_type == 'supercombo':
     assert args.supercombo_onnx
-    policy_runners = [OnnxRunner(args.supercombo_onnx)]
-    output_data['metadata'] = {'model': make_metadata_dict(args.supercombo_onnx)}
-  elif args.model_type == 'vision_multi_policy':
-    assert vision_runner
-    policy_runners, policy_names = _load_policy_runners(args)
-    output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx)}
-    for name in policy_names:
-      runner_arg = getattr(args, f"{name}_onnx")
-      output_data['metadata'][name] = make_metadata_dict(runner_arg)
+    model_metadata = make_metadata_dict(args.supercombo_onnx)
+    output_data['metadata'] = {'model': model_metadata, **model_metadata}
+    output_data['input_devices'] = {'model': Device.DEFAULT}
+    output_data['run_model'] = {}
+    derived_frame_skip = args.frame_skip or derive_frame_skip({}, model_metadata['input_shapes'])
+    model_runner = OnnxRunner(args.supercombo_onnx)
+    run_policy = stock.make_run_policy(model_runner, model_metadata, derived_frame_skip)
+    for cam_w, cam_h in args.camera_resolutions:
+      print(f"Compiling unified run_model JIT for {cam_w}x{cam_h}...")
+      nv12 = stock.NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
+      frame_copy_size = stock.nv12_copy_size(nv12.stride, nv12.y_height, nv12.uv_height)
+      make_model_queues = partial(stock.make_input_queues, model_metadata['input_shapes'], derived_frame_skip,
+                                  frame_copy_size=frame_copy_size)
+      warp = stock.make_warp(nv12, model_w, model_h)
+      run_model_jit = TinyJit(stock.make_run_model(warp, run_policy, model_metadata, frame_copy_size), prune=True)
+      output_data['run_model'][(cam_w, cam_h)] = compile_jit(run_model_jit, stock.MODELD_INPUTS, make_model_queues, benchmark_runs=args.benchmark_runs)
+  else:
+    vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None
+    if args.model_type == 'vision_policy':
+      assert vision_runner and args.policy_onnx
+      policy_runners = [OnnxRunner(args.policy_onnx)]
+      output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx), 'policy': make_metadata_dict(args.policy_onnx)}
+    elif args.model_type == 'vision_multi_policy':
+      assert vision_runner
+      policy_runners, policy_names = _load_policy_runners(args)
+      output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx)}
+      for name in policy_names:
+        runner_arg = getattr(args, f"{name}_onnx")
+        output_data['metadata'][name] = make_metadata_dict(runner_arg)
 
-  policy_keys = [key for key in output_data['metadata'].keys() if key != 'vision']
-  first_policy_meta = output_data['metadata'][policy_keys[0]] if policy_keys else {}
-  vision_meta = output_data['metadata'].get('vision', {})
+    policy_keys = [key for key in output_data['metadata'].keys() if key != 'vision']
+    first_policy_meta = output_data['metadata'][policy_keys[0]] if policy_keys else {}
+    vision_meta = output_data['metadata'].get('vision', {})
 
-  derived_frame_skip = args.frame_skip or derive_frame_skip(vision_meta.get('input_shapes', {}), first_policy_meta.get('input_shapes', {}))
-  all_shapes = {key: value for meta in output_data['metadata'].values() for key, value in meta['input_shapes'].items()}
-  feat_meta = output_data['metadata'].get('vision') or output_data['metadata'].get('model') or output_data['metadata'].get('policy')
-  assert feat_meta is not None
-  features_slice = feat_meta['output_slices']['hidden_state']
-  is_supercombo = vision_runner is None
+    derived_frame_skip = args.frame_skip or derive_frame_skip(vision_meta.get('input_shapes', {}), first_policy_meta.get('input_shapes', {}))
+    all_shapes = {key: value for meta in output_data['metadata'].values() for key, value in meta['input_shapes'].items()}
+    feat_meta = output_data['metadata'].get('vision') or output_data['metadata'].get('policy')
+    assert feat_meta is not None
+    features_slice = feat_meta['output_slices']['hidden_state']
 
-  print(f"Compiling run_policy JIT (model_size={model_w}x{model_h}, frame_skip={derived_frame_skip})...")
-  run_policy_func = make_run_policy(vision_runner, policy_runners, features_slice, derived_frame_skip, all_shapes)
-  run_policy_jit = TinyJit(run_policy_func, prune=True)
-  make_policy_queues = partial(generate_queues_and_npy, all_shapes, derived_frame_skip, is_supercombo=is_supercombo)
-  make_random_model_inputs = partial(make_random_images, keys=['warped'], shape=(2, 6, model_h // 2, model_w // 2), device=Device.DEFAULT)
-  output_data['run_policy'] = compile_jit(run_policy_jit, make_random_model_inputs, POLICY_INPUTS, make_policy_queues)
+    print(f"Compiling run_policy JIT (model_size={model_w}x{model_h}, frame_skip={derived_frame_skip})...")
+    run_policy_func = make_run_policy(vision_runner, policy_runners, features_slice, derived_frame_skip, all_shapes)
+    run_policy_jit = TinyJit(run_policy_func, prune=True)
+    make_policy_queues = partial(generate_queues_and_npy, all_shapes, derived_frame_skip, is_supercombo=False)
+    make_random_model_inputs = partial(make_random_images, keys=['warped'], shape=(2, 6, model_h // 2, model_w // 2), device=Device.DEFAULT)
+    output_data['run_policy'] = compile_jit(run_policy_jit, POLICY_INPUTS, make_policy_queues, make_random_inputs=make_random_model_inputs)
 
-  for cam_w, cam_h in args.camera_resolutions:
-    print(f"Compiling warp JIT for {cam_w}x{cam_h}...")
-    nv12 = NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
-    make_random_warp_inputs = partial(make_random_images, keys=['frame', 'big_frame'], shape=nv12.size, device=Device.DEFAULT)
-    warp = TinyJit(make_warp(nv12, model_w, model_h), prune=True)
-    output_data[(cam_w, cam_h)] = compile_jit(warp, make_random_warp_inputs, WARP_INPUTS, make_warp_queues)
+    for cam_w, cam_h in args.camera_resolutions:
+      print(f"Compiling warp JIT for {cam_w}x{cam_h}...")
+      nv12 = stock.NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
+      frame_copy_size = stock.nv12_copy_size(nv12.stride, nv12.y_height, nv12.uv_height)
+      make_random_warp_inputs = partial(make_random_images, keys=['frame', 'big_frame'], shape=frame_copy_size, device=Device.DEFAULT)
+      warp = TinyJit(stock.make_warp(nv12, model_w, model_h), prune=True)
+      output_data[(cam_w, cam_h)] = compile_jit(warp, WARP_INPUTS, make_warp_queues, make_random_inputs=make_random_warp_inputs)
 
-  output_data['metadata']['warp_dev'] = Device.DEFAULT
+    output_data['metadata']['warp_dev'] = Device.DEFAULT
 
   with open(args.output, "wb") as file:
     dump_oob(output_data, file)
diff --git a/openpilot/sunnypilot/modeld_v2/constants.py b/openpilot/sunnypilot/modeld_v2/constants.py
index cf5157591e..c51996b537 100644
--- a/openpilot/sunnypilot/modeld_v2/constants.py
+++ b/openpilot/sunnypilot/modeld_v2/constants.py
@@ -14,6 +14,8 @@ class ModelConstants:
 
   # model inputs constants
   MODEL_FREQ = 20
+  MODEL_RUN_FREQ = 20
+  MODEL_CONTEXT_FREQ = 5
   FEATURE_LEN = 512
   FULL_HISTORY_BUFFER_LEN = 99
   DESIRE_LEN = 8
@@ -35,6 +37,7 @@ class ModelConstants:
   LANE_LINES_WIDTH = 2
   ROAD_EDGES_WIDTH = 2
   PLAN_WIDTH = 15
+  ACTION_WIDTH = 2
   DESIRE_PRED_WIDTH = 8
   LAT_PLANNER_SOLUTION_WIDTH = 4
   DESIRED_CURV_WIDTH = 1
diff --git a/openpilot/sunnypilot/modeld_v2/meta_helper.py b/openpilot/sunnypilot/modeld_v2/meta_helper.py
index bcf73adc6f..bf4116bb9b 100644
--- a/openpilot/sunnypilot/modeld_v2/meta_helper.py
+++ b/openpilot/sunnypilot/modeld_v2/meta_helper.py
@@ -1,26 +1,9 @@
 from openpilot.sunnypilot.modeld_v2.constants import Meta
-from openpilot.cereal import custom
 from openpilot.sunnypilot.modeld_v2.meta_20hz import Meta20hz
 from openpilot.sunnypilot.models.helpers import get_active_bundle
 
-ModelBundle = custom.ModelManagerSP.ModelBundle
-
 
 def load_meta_constants():
-  """
-  Determines and loads the appropriate meta model class based on the metadata provided. The function checks
-  specific keys and conditions within the provided metadata dictionary to identify the corresponding meta
-  model class to return.
-
-  :param model_metadata: Dictionary containing metadata about the model. It includes
-      details such as input shapes, output slices, and other configurations for identifying
-      metadata-dependent meta model classes.
-  :type model_metadata: dict
-  :return: The appropriate meta model class (Meta, MetaSimPose, or MetaTombRaider)
-      based on the conditions and metadata provided.
-  :rtype: type
-  """
   if (bundle := get_active_bundle()) and bundle.is20hz:
     return Meta20hz
-
-  return Meta  # Default
+  return Meta
diff --git a/openpilot/sunnypilot/modeld_v2/modeld.py b/openpilot/sunnypilot/modeld_v2/modeld.py
index 2ab96934ef..683def6588 100755
--- a/openpilot/sunnypilot/modeld_v2/modeld.py
+++ b/openpilot/sunnypilot/modeld_v2/modeld.py
@@ -38,11 +38,18 @@ from openpilot.selfdrive.controls.lib.desire_helper import DesireHelper
 from openpilot.selfdrive.controls.lib.drive_helpers import get_accel_from_plan, smooth_value
 from openpilot.selfdrive.modeld.modeld import ChestnutState
 
+from openpilot.selfdrive.modeld.compile_modeld import (
+  MODELD_INPUTS,
+  make_input_queues as make_stock_input_queues,
+)
 from openpilot.sunnypilot.modeld_v2.fill_model_msg import fill_model_msg, fill_pose_msg, PublishState, get_curvature_from_output
-from openpilot.sunnypilot.modeld_v2.constants import Plan
+from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser
+from openpilot.sunnypilot.modeld_v2.constants import ModelConstants, Plan
 from openpilot.sunnypilot.modeld_v2.meta_helper import load_meta_constants
 from openpilot.sunnypilot.modeld_v2.camera_offset_helper import CameraOffsetHelper
-from openpilot.sunnypilot.modeld_v2.compile_modeld import derive_frame_skip, make_split_input_queues, make_supercombo_input_queues, WARP_INPUTS, POLICY_INPUTS
+from openpilot.sunnypilot.modeld_v2.compile_modeld import (derive_frame_skip, make_split_input_queues,
+                                                           make_supercombo_input_queues, nv12_copy_size,
+                                                           WARP_INPUTS, POLICY_INPUTS)
 from openpilot.sunnypilot.livedelay.helpers import get_lat_delay
 from openpilot.sunnypilot.modeld_v2.modeld_base import ModelStateBase
 from openpilot.sunnypilot.models.helpers import get_active_bundle
@@ -112,29 +119,39 @@ class ModelState(ModelStateBase):
     jits = load_oob(open_file_chunked(pkl_path))
 
     metadata = jits['metadata']
-    self.WARP_DEV = metadata.get('warp_dev', 'QCOM' if COMMA_HARDWARE else 'CPU')
-    self.DEV = 'AMD' if self.chestnut else ('QCOM' if COMMA_HARDWARE else 'CPU')
+    self.WARP_DEV = metadata.get('warp_dev', 'QCOM') if COMMA_HARDWARE else 'CPU'
+    self.DEV = ('AMD' if self.chestnut else 'QCOM') if COMMA_HARDWARE else 'CPU'
     self.QUEUE_DEV = self.DEV
-    self.run_policy = jits['run_policy']
-    self.warp = jits[(cam_w, cam_h)]
+    self.is_run_model = 'run_model' in jits
 
-    if 'model' in metadata:
-      model_metadata = metadata['model']
+    nv12_info = get_nv12_info(cam_w, cam_h)
+    self.frame_copy_size = nv12_copy_size(*nv12_info[:3])
+    self.full_frames: dict = {}
+    self._blob_cache: dict = {}
+    self.frame_buffers: dict = {}
+
+    if self.is_run_model or 'model' in metadata:
+      model_metadata = metadata.get('model', metadata)
+      self.input_shapes = model_metadata['input_shapes']
       self.vision_output_slices = model_metadata['output_slices']
       self.policy_output_slices = {}
       self._policy_slices_list = []
       self._combined_model_type = 'supercombo'
-      self._vision_input_names = [key for key in model_metadata['input_shapes'] if 'img' in key]
-      frame_skip = derive_frame_skip({}, model_metadata['input_shapes'])
-      self.input_queues, self.numpy_inputs = make_supercombo_input_queues(model_metadata['input_shapes'],
-                                                                          frame_skip, device=self.QUEUE_DEV)
-    else:
-      vision_metadata = metadata['vision']
-      policy_keys = [k for k in metadata if k != 'vision']
-      if policy_keys == ['policy']:
-        self._combined_model_type = 'split'
+      self._vision_input_names = [key for key in self.input_shapes if 'img' in key]
+      self.frame_skip = derive_frame_skip({}, self.input_shapes)
+      if self.is_run_model:
+        self.input_queues, self.numpy_inputs, self.frame_buffers = make_stock_input_queues(
+          self.input_shapes, self.frame_skip, device=self.DEV, frame_copy_size=self.frame_copy_size)
+        self.frame_views, self.npy = self.frame_buffers, self.numpy_inputs
+        self.run_model, self.run_policy, self.warp = jits['run_model'][(cam_w, cam_h)], None, None
       else:
-        self._combined_model_type = 'multi_policy'
+        self.input_queues, self.numpy_inputs = make_supercombo_input_queues(self.input_shapes, self.frame_skip, device=self.QUEUE_DEV)
+        self.run_model, self.run_policy, self.warp = None, jits['run_policy'], jits[(cam_w, cam_h)]
+    else:
+      self.run_model, self.run_policy, self.warp = None, jits['run_policy'], jits[(cam_w, cam_h)]
+      vision_metadata = metadata['vision']
+      policy_keys = [k for k in metadata if k not in ('vision', 'warp_dev')]
+      self._combined_model_type = 'split' if policy_keys == ['policy'] else 'multi_policy'
       self.vision_output_slices = vision_metadata['output_slices']
       self._policy_keys = policy_keys
       self._policy_slices_list = [metadata[k]['output_slices'] for k in policy_keys]
@@ -150,50 +167,39 @@ class ModelState(ModelStateBase):
     self._desire_key = next(key for key in self.numpy_inputs if key.startswith('desire'))
     self._road_key = next(key for key in self._vision_input_names if 'big' not in key)
     self._wide_key = next(key for key in self._vision_input_names if 'big' in key)
+    self.frame_buf_params = dict.fromkeys(self._vision_input_names, nv12_info)
 
     is_20hz = bundle.is20hz if bundle else self._combined_model_type in ('split', 'multi_policy')
     if is_20hz:
       from openpilot.sunnypilot.models.split_model_constants import SplitModelConstants
       self.constants = SplitModelConstants()
     else:
-      from openpilot.sunnypilot.modeld_v2.constants import ModelConstants
       self.constants = ModelConstants()
 
-    if self._combined_model_type != 'supercombo':
-      from openpilot.sunnypilot.modeld_v2.parse_model_outputs_split import Parser as SplitParser
-      self.parser = SplitParser()
-    else:
-      from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser as CombinedParser
-      self.parser = CombinedParser()
-
+    self.parser = Parser()
     self.prev_desire = np.zeros(self.constants.DESIRE_LEN, dtype=np.float32)
-    self.full_frames: dict = {}
-    self._blob_cache: dict = {}
-    nv12_info = get_nv12_info(cam_w, cam_h)
-    self.frame_buf_params = dict.fromkeys(self._vision_input_names, nv12_info)
 
-    yuv_size = self.frame_buf_params[self._road_key][3]
-    frame_tensor = Tensor(np.zeros(yuv_size, dtype=np.uint8), device=self.WARP_DEV).contiguous().realize()
-    big_frame_tensor = Tensor(np.zeros(yuv_size, dtype=np.uint8), device=self.WARP_DEV).contiguous().realize()
-    self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=frame_tensor, big_frame=big_frame_tensor)
+    if self.warp is not None:
+      self.full_frames = {k: Tensor(np.zeros(nv12_info[3], dtype=np.uint8), device=self.WARP_DEV).contiguous().realize() for k in self._vision_input_names}
+      self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[self._road_key], big_frame=self.full_frames[self._wide_key])
 
   def warmup(self) -> None:
-    dummy_frames = {k: np.zeros(self.frame_buf_params[k][3], dtype=np.uint8) for k in self._vision_input_names}
+    dummy_size = self.frame_copy_size if self.is_run_model else self.frame_buf_params[self._road_key][3]
+    dummy_frames = {k: np.zeros(dummy_size, dtype=np.uint8) for k in self._vision_input_names}
     transforms = {k: np.eye(3, dtype=np.float32) for k in [self._road_key, self._wide_key] if k}
-
-    dummy_inputs = {}
-    for k, v in self.numpy_inputs.items():
-      if k not in ['tfm', 'big_tfm', 'prev_feat']:
-        dummy_inputs[k] = np.zeros(v.shape, dtype=v.dtype)
-
-    self.run(dummy_frames, transforms, dummy_inputs, prepare_only=False)
-
-    for v in self.numpy_inputs.values():
-      v[:] = 0
+    dummy_inputs = {k: np.zeros(v.shape, dtype=v.dtype) for k, v in self.numpy_inputs.items() if k not in ['tfm', 'big_tfm', 'prev_feat']}
+    self.run(dummy_frames, transforms, dummy_inputs)
+    if self.is_run_model:
+      self.input_queues, self.numpy_inputs, self.frame_buffers = make_stock_input_queues(
+        self.input_shapes, self.frame_skip, device=self.DEV, frame_copy_size=self.frame_copy_size)
+      self.frame_views = self.frame_buffers
+      self.npy = self.numpy_inputs
+    else:
+      for v in self.numpy_inputs.values():
+        v[:] = 0
+      self.full_frames.clear()
+      self._blob_cache.clear()
     self.prev_desire[:] = 0
-    self.full_frames.clear()
-    self._blob_cache.clear()
-
 
   @property
   def mlsim(self) -> bool:
@@ -208,34 +214,40 @@ class ModelState(ModelStateBase):
     return self._desire_key
 
   def run(self, bufs: dict[str, VisionBuf], transforms: dict[str, np.ndarray],
-          inputs: dict[str, np.ndarray], prepare_only: bool,
+          inputs: dict[str, np.ndarray],
           after_enqueue: Callable[[], None] | None = None) -> dict[str, np.ndarray] | None:
-    for key in bufs.keys():
-      ptr = np.frombuffer(bufs[key].data, dtype=np.uint8).ctypes.data
-      yuv_size = self.frame_buf_params[key][3]
-      cache_key = (key, ptr)
-      if cache_key not in self._blob_cache:
-        self._blob_cache[cache_key] = Tensor.from_blob(ptr, (yuv_size,), dtype='uint8', device=self.WARP_DEV)
-      self.full_frames[key] = self._blob_cache[cache_key]
+    if self.is_run_model:
+      for key, buf in bufs.items():
+        data = buf.data if hasattr(buf, 'data') else buf
+        np.copyto(self.frame_buffers[key], np.frombuffer(data, dtype=np.uint8, count=self.frame_copy_size))
+    else:
+      for key, buf in bufs.items():
+        ptr = np.frombuffer(buf.data, dtype=np.uint8).ctypes.data
+        cache_key = (key, ptr)
+        if cache_key not in self._blob_cache:
+          self._blob_cache[cache_key] = Tensor.from_blob(ptr, (self.frame_buf_params[key][3],), dtype='uint8', device=self.WARP_DEV)
+        self.full_frames[key] = self._blob_cache[cache_key]
 
     desire_key = self.desire_key
     inputs[desire_key][0] = 0
     self.numpy_inputs[desire_key][:] = np.where(inputs[desire_key] - self.prev_desire > .99, inputs[desire_key], 0)
     self.prev_desire[:] = inputs[desire_key]
+
     for key in ('traffic_convention', 'lateral_control_params', 'action_t'):
       if key in self.numpy_inputs and key in inputs:
         self.numpy_inputs[key][:] = inputs[key]
 
-    road_key = self._road_key
-    wide_key = self._wide_key
-    self.numpy_inputs['tfm'][:, :] = transforms[road_key].reshape(3, 3)
-    self.numpy_inputs['big_tfm'][:, :] = transforms[wide_key].reshape(3, 3)
+    self.numpy_inputs['tfm'][:, :] = transforms[self._road_key].reshape(3, 3)
+    self.numpy_inputs['big_tfm'][:, :] = transforms[self._wide_key].reshape(3, 3)
+
+    if self.run_model is not None:
+      outs, = self.run_model(**{k: self.input_queues[k] for k in MODELD_INPUTS})
+      raw_outputs = outs
+    else:
+      assert self.warp is not None and self.run_policy is not None
+      warped = self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[self._road_key], big_frame=self.full_frames[self._wide_key])
+      raw_outputs = self.run_policy(**{k: self.input_queues[k] for k in POLICY_INPUTS if k in self.input_queues}, warped=warped)
 
-    if prepare_only:
-      self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
-      return None
-    warped = self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
-    raw_outputs = self.run_policy(**{k: self.input_queues[k] for k in POLICY_INPUTS if k in self.input_queues}, warped=warped)
     if after_enqueue is not None:
       after_enqueue()
 
@@ -245,7 +257,7 @@ class ModelState(ModelStateBase):
         raise RuntimeError("model output not finite")
       sliced = {k: model_output[np.newaxis, v] for k, v in self.vision_output_slices.items()}
       outputs = self.parser.parse_outputs(sliced)
-      if 'prev_feat' in self.numpy_inputs:
+      if 'prev_feat' in self.numpy_inputs and 'hidden_state' in self.vision_output_slices:
         self.numpy_inputs['prev_feat'][:] = model_output[self.vision_output_slices['hidden_state']]
     else:
       vision_output = raw_outputs[0].numpy().flatten()
@@ -360,7 +372,11 @@ def main(demo=False):
     loader.start()
     loader.join(BIG_MODEL_TIMEOUT)
     model = big_model
+    if model is None:
+      params.put_bool("ChestnutModelError", True)
     params.put_bool("ChestnutActive", model is not None)
+    if model is not None:
+      params.remove("ChestnutModelError")
 
   small_model = ModelState(cam_w=vipc_client_main.width, cam_h=vipc_client_main.height, chestnut=False) if model is None or CHESTNUT else None
   if model is None:
@@ -474,9 +490,6 @@ def main(demo=False):
     run_count = run_count + 1
 
     frame_drop_ratio = frames_dropped / (1 + frames_dropped)
-    prepare_only = vipc_dropped_frames > 0
-    if prepare_only:
-      cloudlog.error(f"skipping model eval. Dropped {vipc_dropped_frames} frames")
 
     bufs = {name: buf_extra if 'big' in name else buf_main for name in model.vision_input_names}
     transforms = {name: model_transform_extra if 'big' in name else model_transform_main for name in model.vision_input_names}
@@ -501,11 +514,12 @@ def main(demo=False):
     try:
       send_chestnut = (chestnut_state is not None and
                        run_count % round(model.constants.MODEL_FREQ / SERVICE_LIST['chestnutState'].frequency) == 0)
-      model_output = model.run(bufs, transforms, inputs, prepare_only, chestnut_state.send if send_chestnut else None)
+      model_output = model.run(bufs, transforms, inputs, chestnut_state.send if send_chestnut else None)
     except Exception:
       if not params.get_bool("ChestnutActive"):
         raise
       cloudlog.exception("chestnut failed, falling back to small")
+      params.put_bool("ChestnutModelError", True)
       params.put_bool("ChestnutActive", False)
       assert small_model is not None
       model = small_model
diff --git a/openpilot/sunnypilot/modeld_v2/parse_model_outputs.py b/openpilot/sunnypilot/modeld_v2/parse_model_outputs.py
index 7a3adcc1fa..d6cfdbbc88 100644
--- a/openpilot/sunnypilot/modeld_v2/parse_model_outputs.py
+++ b/openpilot/sunnypilot/modeld_v2/parse_model_outputs.py
@@ -115,22 +115,41 @@ class Parser:
     outs[name + '_stds'] = pred_std_final.reshape(final_shape)
 
   def parse_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
-    # supercombo (4955 / 102) and newer variants (e.g. 990 / 144).
-    self.parse_mdn('plan',   outs, out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
-    self.parse_mdn('lane_lines', outs, out_shape=(ModelConstants.NUM_LANE_LINES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
-    self.parse_mdn('road_edges', outs, out_shape=(ModelConstants.NUM_ROAD_EDGES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
-    self.parse_mdn('pose',         outs, out_shape=(ModelConstants.POSE_WIDTH,))
-    self.parse_mdn('road_transform', outs, out_shape=(ModelConstants.POSE_WIDTH,))
+    if 'plan' in outs:
+      self.parse_mdn('plan', outs, out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
+    if 'planplus' in outs:
+      self.parse_mdn('planplus', outs, out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
+    if 'lane_lines' in outs:
+      self.parse_mdn('lane_lines', outs, out_shape=(ModelConstants.NUM_LANE_LINES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
+    if 'road_edges' in outs:
+      self.parse_mdn('road_edges', outs, out_shape=(ModelConstants.NUM_ROAD_EDGES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
+    if 'pose' in outs:
+      self.parse_mdn('pose', outs, out_shape=(ModelConstants.POSE_WIDTH,))
+    if 'road_transform' in outs:
+      self.parse_mdn('road_transform', outs, out_shape=(ModelConstants.POSE_WIDTH,))
     if 'sim_pose' in outs:
       self.parse_mdn('sim_pose', outs, out_shape=(ModelConstants.POSE_WIDTH,))
-    self.parse_mdn('wide_from_device_euler', outs, out_shape=(ModelConstants.WIDE_FROM_DEVICE_WIDTH,))
-    self.parse_mdn('lead', outs, out_shape=(ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH))
+    if 'wide_from_device_euler' in outs:
+      self.parse_mdn('wide_from_device_euler', outs, out_shape=(ModelConstants.WIDE_FROM_DEVICE_WIDTH,))
+    if 'lead' in outs:
+      self.parse_mdn('lead', outs, out_shape=(ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH))
     if 'lat_planner_solution' in outs:
       self.parse_mdn('lat_planner_solution', outs, out_shape=(ModelConstants.IDX_N, ModelConstants.LAT_PLANNER_SOLUTION_WIDTH))
     if 'desired_curvature' in outs:
       self.parse_mdn('desired_curvature', outs, out_shape=(ModelConstants.DESIRED_CURV_WIDTH,))
+    if 'action' in outs:
+      self.parse_mdn('action', outs, out_shape=(ModelConstants.ACTION_WIDTH,))
     for k in ['lead_prob', 'lane_lines_prob', 'meta']:
-      self.parse_binary_crossentropy(k, outs)
-    self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
-    self.parse_categorical_crossentropy('desire_pred',  outs, out_shape=(ModelConstants.DESIRE_PRED_LEN, ModelConstants.DESIRE_PRED_WIDTH))
+      if k in outs:
+        self.parse_binary_crossentropy(k, outs)
+    if 'desire_state' in outs:
+      self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
+    if 'desire_pred' in outs:
+      self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(ModelConstants.DESIRE_PRED_LEN, ModelConstants.DESIRE_PRED_WIDTH))
     return outs
+
+  def parse_vision_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
+    return self.parse_outputs(outs)
+
+  def parse_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
+    return self.parse_outputs(outs)
diff --git a/openpilot/sunnypilot/modeld_v2/parse_model_outputs_split.py b/openpilot/sunnypilot/modeld_v2/parse_model_outputs_split.py
deleted file mode 100644
index 3db47aee42..0000000000
--- a/openpilot/sunnypilot/modeld_v2/parse_model_outputs_split.py
+++ /dev/null
@@ -1,159 +0,0 @@
-import numpy as np
-from openpilot.sunnypilot.models.split_model_constants import SplitModelConstants
-
-
-def safe_exp(x, out=None):
-  # -11 is around 10**14, more causes float16 overflow
-  return np.exp(np.clip(x, -np.inf, 11), out=out)
-
-
-def sigmoid(x):
-  return 1. / (1. + safe_exp(-x))
-
-
-def softmax(x, axis=-1):
-  x -= np.max(x, axis=axis, keepdims=True)
-  if x.dtype == np.float32 or x.dtype == np.float64:
-    safe_exp(x, out=x)
-  else:
-    x = safe_exp(x)
-  x /= np.sum(x, axis=axis, keepdims=True)
-  return x
-
-
-class Parser:
-  def __init__(self, ignore_missing=False):
-    self.ignore_missing = ignore_missing
-
-  def check_missing(self, outs, name):
-    if name not in outs and not self.ignore_missing:
-      raise ValueError(f"Missing output {name}")
-    return name not in outs
-
-  def parse_categorical_crossentropy(self, name, outs, out_shape=None):
-    if self.check_missing(outs, name):
-      return
-    raw = outs[name]
-    if out_shape is not None:
-      raw = raw.reshape((raw.shape[0],) + out_shape)
-    outs[name] = softmax(raw, axis=-1)
-
-  def parse_binary_crossentropy(self, name, outs):
-    if self.check_missing(outs, name):
-      return
-    raw = outs[name]
-    outs[name] = sigmoid(raw)
-
-  def parse_mdn(self, name, outs, in_N=0, out_N=1, out_shape=None):
-    if self.check_missing(outs, name):
-      return
-    raw = outs[name]
-    raw = raw.reshape((raw.shape[0], max(in_N, 1), -1))
-
-    n_values = (raw.shape[2] - out_N)//2
-    pred_mu = raw[:,:,:n_values]
-    pred_std = safe_exp(raw[:,:,n_values: 2*n_values])
-
-    if in_N > 1:
-      weights = np.zeros((raw.shape[0], in_N, out_N), dtype=raw.dtype)
-      for i in range(out_N):
-        weights[:,:,i - out_N] = softmax(raw[:,:,i - out_N], axis=-1)
-
-      if out_N == 1:
-        for fidx in range(weights.shape[0]):
-          idxs = np.argsort(weights[fidx][:,0])[::-1]
-          weights[fidx] = weights[fidx][idxs]
-          pred_mu[fidx] = pred_mu[fidx][idxs]
-          pred_std[fidx] = pred_std[fidx][idxs]
-      assert out_shape is not None
-      full_shape = tuple([raw.shape[0], in_N] + list(out_shape))
-      outs[name + '_weights'] = weights
-      outs[name + '_hypotheses'] = pred_mu.reshape(full_shape)
-      outs[name + '_stds_hypotheses'] = pred_std.reshape(full_shape)
-
-      pred_mu_final = np.zeros((raw.shape[0], out_N, n_values), dtype=raw.dtype)
-      pred_std_final = np.zeros((raw.shape[0], out_N, n_values), dtype=raw.dtype)
-      for fidx in range(weights.shape[0]):
-        for hidx in range(out_N):
-          idxs = np.argsort(weights[fidx,:,hidx])[::-1]
-          pred_mu_final[fidx, hidx] = pred_mu[fidx, idxs[0]]
-          pred_std_final[fidx, hidx] = pred_std[fidx, idxs[0]]
-    else:
-      pred_mu_final = pred_mu
-      pred_std_final = pred_std
-
-    if out_N > 1:
-      assert out_shape is not None
-      final_shape = tuple([raw.shape[0], out_N] + list(out_shape))
-    else:
-      assert out_shape is not None
-      final_shape = tuple([raw.shape[0],] + list(out_shape))
-    outs[name] = pred_mu_final.reshape(final_shape)
-    outs[name + '_stds'] = pred_std_final.reshape(final_shape)
-
-  def is_mhp(self, outs, name, shape):
-    if self.check_missing(outs, name):
-      return False
-    if outs[name].shape[1] == 2 * shape:
-      return False
-    return True
-
-  def parse_dynamic_outputs(self, outs: dict[str, np.ndarray]) -> None:
-    if 'lead' in outs:
-      lead_mhp = self.is_mhp(outs, 'lead',
-                             SplitModelConstants.LEAD_MHP_SELECTION * SplitModelConstants.LEAD_TRAJ_LEN * SplitModelConstants.LEAD_WIDTH)
-      lead_in_N, lead_out_N = (SplitModelConstants.LEAD_MHP_N, SplitModelConstants.LEAD_MHP_SELECTION) if lead_mhp else (0, 0)
-      lead_out_shape = (SplitModelConstants.LEAD_TRAJ_LEN, SplitModelConstants.LEAD_WIDTH) if lead_mhp else \
-        (SplitModelConstants.LEAD_MHP_SELECTION, SplitModelConstants.LEAD_TRAJ_LEN, SplitModelConstants.LEAD_WIDTH)
-      self.parse_mdn('lead', outs, in_N=lead_in_N, out_N=lead_out_N, out_shape=lead_out_shape)
-    if 'plan' in outs:
-      plan_mhp = self.is_mhp(outs, 'plan', SplitModelConstants.IDX_N * SplitModelConstants.PLAN_WIDTH)
-      plan_in_N, plan_out_N = (SplitModelConstants.PLAN_MHP_N, SplitModelConstants.PLAN_MHP_SELECTION) if plan_mhp else (0, 0)
-      self.parse_mdn('plan', outs, in_N=plan_in_N, out_N=plan_out_N,
-                     out_shape=(SplitModelConstants.IDX_N, SplitModelConstants.PLAN_WIDTH))
-    if 'planplus' in outs:
-      self.parse_mdn('planplus', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.IDX_N, SplitModelConstants.PLAN_WIDTH))
-
-  def split_outputs(self, outs: dict[str, np.ndarray]) -> None:
-    if 'desired_curvature' in outs:
-      self.parse_mdn('desired_curvature', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.DESIRED_CURV_WIDTH,))
-    if 'desire_pred' in outs:
-      self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(SplitModelConstants.DESIRE_PRED_LEN,SplitModelConstants.DESIRE_PRED_WIDTH))
-    if 'desire_state' in outs:
-      self.parse_categorical_crossentropy('desire_state', outs, out_shape=(SplitModelConstants.DESIRE_PRED_WIDTH,))
-    if 'lane_lines' in outs:
-      self.parse_mdn('lane_lines', outs, in_N=0, out_N=0,
-                     out_shape=(SplitModelConstants.NUM_LANE_LINES,SplitModelConstants.IDX_N,SplitModelConstants.LANE_LINES_WIDTH))
-    if 'lane_lines_prob' in outs:
-      self.parse_binary_crossentropy('lane_lines_prob', outs)
-    if 'lead_prob' in outs:
-      self.parse_binary_crossentropy('lead_prob', outs)
-    if 'lat_planner_solution' in outs:
-      self.parse_mdn('lat_planner_solution', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.IDX_N,SplitModelConstants.LAT_PLANNER_SOLUTION_WIDTH))
-    if 'meta' in outs:
-      self.parse_binary_crossentropy('meta', outs)
-    if 'road_edges' in outs:
-      self.parse_mdn('road_edges', outs, in_N=0, out_N=0,
-                     out_shape=(SplitModelConstants.NUM_ROAD_EDGES,SplitModelConstants.IDX_N,SplitModelConstants.LANE_LINES_WIDTH))
-    if 'sim_pose' in outs:
-      self.parse_mdn('sim_pose', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.POSE_WIDTH,))
-    if 'action' in outs:
-      self.parse_mdn('action', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.ACTION_WIDTH,))
-
-  def parse_vision_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
-    self.parse_mdn('pose', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.POSE_WIDTH,))
-    self.parse_mdn('wide_from_device_euler', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.WIDE_FROM_DEVICE_WIDTH,))
-    self.parse_mdn('road_transform', outs, in_N=0, out_N=0, out_shape=(SplitModelConstants.POSE_WIDTH,))
-    self.parse_dynamic_outputs(outs)
-    self.split_outputs(outs)
-    return outs
-
-  def parse_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
-    self.parse_dynamic_outputs(outs)
-    self.split_outputs(outs)
-    return outs
-
-  def parse_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
-    outs = self.parse_vision_outputs(outs)
-    outs = self.parse_policy_outputs(outs)
-    return outs
diff --git a/openpilot/sunnypilot/modeld_v2/tests/helpers.py b/openpilot/sunnypilot/modeld_v2/tests/helpers.py
index 82e159a305..8f148f6789 100644
--- a/openpilot/sunnypilot/modeld_v2/tests/helpers.py
+++ b/openpilot/sunnypilot/modeld_v2/tests/helpers.py
@@ -117,7 +117,7 @@ ARCHETYPES = {
     is_20hz=True,
     expected_model_type='split',
     expected_constants_class=SplitModelConstants,
-    expected_parser_module='parse_model_outputs_split',
+    expected_parser_module='parse_model_outputs',
     expected_desire_key='desire',
   ),
   'vision_multi_policy': Archetype(
@@ -130,7 +130,7 @@ ARCHETYPES = {
     is_20hz=True,
     expected_model_type='multi_policy',
     expected_constants_class=SplitModelConstants,
-    expected_parser_module='parse_model_outputs_split',
+    expected_parser_module='parse_model_outputs',
     expected_desire_key='desire',
   ),
   'tri_policy': Archetype(
@@ -144,7 +144,7 @@ ARCHETYPES = {
     is_20hz=True,
     expected_model_type='multi_policy',
     expected_constants_class=SplitModelConstants,
-    expected_parser_module='parse_model_outputs_split',
+    expected_parser_module='parse_model_outputs',
     expected_desire_key='desire',
   ),
   'supercombo_non20hz': Archetype(
diff --git a/openpilot/sunnypilot/modeld_v2/tests/test_combined_pkl_loader.py b/openpilot/sunnypilot/modeld_v2/tests/test_combined_pkl_loader.py
index e3a686a73f..88cee8c5b4 100644
--- a/openpilot/sunnypilot/modeld_v2/tests/test_combined_pkl_loader.py
+++ b/openpilot/sunnypilot/modeld_v2/tests/test_combined_pkl_loader.py
@@ -103,6 +103,23 @@ class TestStockEquivalence(OpenpilotTestCase):
     assert state.vision_output_slices == arch.metadata_structure['vision']['output_slices']
     assert state.policy_output_slices == arch.metadata_structure['policy']['output_slices']
 
+  def test_unified_run_model(self, tmp_path, monkeypatch, patch_modeld):
+    from openpilot.common.hardware import hw
+    from openpilot.selfdrive.modeld.helpers import dump_oob
+    shapes = {'img': (1, 12, 128, 256), 'big_img': (1, 12, 128, 256), 'features_buffer': (1, 24, 32, 512),
+              'desire_pulse': (1, 25, 8), 'traffic_convention': (1, 2), 'action_t': (1, 2)}
+    pkl_data = {'metadata': {'model': {'input_shapes': shapes, 'output_slices': {}}},
+                'run_model': {(CAM_W, CAM_H): tests_helpers._noop_jit}}
+    with open(tmp_path / 'driving_test_tinygrad.pkl', 'wb') as f:
+      dump_oob(pkl_data, f)
+    bundle = DummyBundle(models=[DummyModel('supercombo', 'driving_test_tinygrad.pkl')])
+    patch_modeld(bundle)
+    monkeypatch.setattr(hw.Paths, 'model_root', staticmethod(lambda: str(tmp_path)))
+    state = ModelState(cam_w=CAM_W, cam_h=CAM_H)
+    assert state.is_run_model and state.run_model is not None
+    assert state.run_policy is None and state.warp is None
+    assert 'img' in state.frame_views and 'big_img' in state.frame_views
+
 
 ARCHETYPE_NAMES = list(ARCHETYPES.keys())
 
diff --git a/openpilot/sunnypilot/modeld_v2/tests/test_parse_model_outputs.py b/openpilot/sunnypilot/modeld_v2/tests/test_parse_model_outputs.py
new file mode 100644
index 0000000000..821043124a
--- /dev/null
+++ b/openpilot/sunnypilot/modeld_v2/tests/test_parse_model_outputs.py
@@ -0,0 +1,81 @@
+import numpy as np
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.sunnypilot.modeld_v2.constants import ModelConstants
+from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser, _infer_mhp, sigmoid, softmax
+
+
+class TestParseModelOutputs(OpenpilotTestCase):
+  def test_infer_mhp_lead(self):
+    in_hypotheses, out_selections = _infer_mhp(102, 24)
+    assert in_hypotheses == 2
+    assert out_selections == 3
+
+  def test_infer_mhp_plan(self):
+    in_hypotheses, out_selections = _infer_mhp(4955, 495)
+    assert in_hypotheses == 5
+    assert out_selections == 1
+
+  def test_infer_mhp_non_mdn(self):
+    in_hypotheses, out_selections = _infer_mhp(48, 24)
+    assert in_hypotheses == 1
+    assert out_selections == 0
+
+  def test_check_missing_raises(self):
+    parser = Parser(ignore_missing=False)
+    with self.assertRaises(ValueError):
+      parser.check_missing({}, "missing_key")
+
+  def test_check_missing_ignored(self):
+    parser = Parser(ignore_missing=True)
+    assert parser.check_missing({}, "missing_key") is True
+
+  def test_binary_crossentropy(self):
+    parser = Parser()
+    raw_logits = np.array([[-10.0, 0.0, 10.0]], dtype=np.float32)
+    outs = {"meta": raw_logits.copy()}
+    parser.parse_binary_crossentropy("meta", outs)
+    expected_probabilities = sigmoid(raw_logits)
+    np.testing.assert_allclose(outs["meta"], expected_probabilities, rtol=1e-5, atol=1e-6)
+
+  def test_categorical_crossentropy(self):
+    parser = Parser()
+    raw_logits = np.array([[1.0, 2.0, 3.0]], dtype=np.float32)
+    outs = {"desire_state": raw_logits.copy()}
+    parser.parse_categorical_crossentropy("desire_state", outs)
+    expected_probabilities = softmax(raw_logits)
+    np.testing.assert_allclose(outs["desire_state"], expected_probabilities, rtol=1e-5, atol=1e-6)
+
+  def test_parse_vision_outputs(self):
+    parser = Parser()
+    pose_raw = np.zeros((1, ModelConstants.POSE_WIDTH * 2), dtype=np.float32)
+    road_transform_raw = np.zeros((1, ModelConstants.POSE_WIDTH * 2), dtype=np.float32)
+    lead_raw = np.zeros((1, 102), dtype=np.float32)
+    meta_raw = np.zeros((1, 55), dtype=np.float32)
+    vision_outputs = {"pose": pose_raw, "road_transform": road_transform_raw, "lead": lead_raw, "meta": meta_raw}
+    parsed = parser.parse_vision_outputs(vision_outputs)
+    assert "pose" in parsed
+    assert "road_transform" in parsed
+    assert "lead" in parsed
+    assert "meta" in parsed
+    assert parsed["pose"].shape == (1, ModelConstants.POSE_WIDTH)
+    assert parsed["lead"].shape == (1, ModelConstants.LEAD_MHP_SELECTION, ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH)
+
+  def test_parse_policy_outputs(self):
+    parser = Parser()
+    plan_raw = np.zeros((1, 4955), dtype=np.float32)
+    desire_state_raw = np.zeros((1, ModelConstants.DESIRE_PRED_WIDTH), dtype=np.float32)
+    action_raw = np.zeros((1, ModelConstants.ACTION_WIDTH * 2), dtype=np.float32)
+    policy_outputs = {"plan": plan_raw, "desire_state": desire_state_raw, "action": action_raw}
+    parsed = parser.parse_policy_outputs(policy_outputs)
+    assert parsed["plan"].shape == (1, ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH)
+    assert parsed["action"].shape == (1, ModelConstants.ACTION_WIDTH)
+    assert parsed["desire_state"].shape == (1, ModelConstants.DESIRE_PRED_WIDTH)
+
+  def test_parse_outputs_combined(self):
+    parser = Parser()
+    outputs = {"plan": np.zeros((1, 4955), dtype=np.float32), "pose": np.zeros((1, ModelConstants.POSE_WIDTH * 2),
+               dtype=np.float32), "meta": np.zeros((1, 55), dtype=np.float32)}
+    parsed = parser.parse_outputs(outputs)
+    assert parsed["plan"].shape == (1, ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH)
+    assert parsed["pose"].shape == (1, ModelConstants.POSE_WIDTH)
+    assert parsed["meta"].shape == (1, 55)
diff --git a/openpilot/sunnypilot/models/constants.py b/openpilot/sunnypilot/models/constants.py
deleted file mode 100644
index 18abc6c960..0000000000
--- a/openpilot/sunnypilot/models/constants.py
+++ /dev/null
@@ -1,121 +0,0 @@
-import numpy as np
-
-def index_function(idx, max_val=192, max_idx=32):
-  return max_val * ((idx/max_idx)**2)
-
-
-class ModelConstants:
-  # time and distance indices
-  IDX_N = 33
-  T_IDXS = [index_function(idx, max_val=10.0) for idx in range(IDX_N)]
-  X_IDXS = [index_function(idx, max_val=192.0) for idx in range(IDX_N)]
-  LEAD_T_IDXS = [0., 2., 4., 6., 8., 10.]
-  LEAD_T_OFFSETS = [0., 2., 4.]
-  META_T_IDXS = [2., 4., 6., 8., 10.]
-
-  # model inputs constants
-  MODEL_FREQ = 20
-  FEATURE_LEN = 512
-  HISTORY_BUFFER_LEN = 99
-  DESIRE_LEN = 8
-  TRAFFIC_CONVENTION_LEN = 2
-  NAV_FEATURE_LEN = 256
-  NAV_INSTRUCTION_LEN = 150
-  LAT_PLANNER_STATE_LEN = 4
-  LATERAL_CONTROL_PARAMS_LEN = 2
-  PREV_DESIRED_CURV_LEN = 1
-
-  # model outputs constants
-  FCW_THRESHOLDS_5MS2 = np.array([.05, .05, .15, .15, .15], dtype=np.float32)
-  FCW_THRESHOLDS_3MS2 = np.array([.7, .7], dtype=np.float32)
-  FCW_5MS2_PROBS_WIDTH = 5
-  FCW_3MS2_PROBS_WIDTH = 2
-
-  DISENGAGE_WIDTH = 5
-  POSE_WIDTH = 6
-  WIDE_FROM_DEVICE_WIDTH = 3
-  SIM_POSE_WIDTH = 6
-  LEAD_WIDTH = 4
-  LANE_LINES_WIDTH = 2
-  ROAD_EDGES_WIDTH = 2
-  PLAN_WIDTH = 15
-  DESIRE_PRED_WIDTH = 8
-  LAT_PLANNER_SOLUTION_WIDTH = 4
-  DESIRED_CURV_WIDTH = 1
-
-  NUM_LANE_LINES = 4
-  NUM_ROAD_EDGES = 2
-
-  LEAD_TRAJ_LEN = 6
-  DESIRE_PRED_LEN = 4
-
-  PLAN_MHP_N = 5
-  LEAD_MHP_N = 2
-  PLAN_MHP_SELECTION = 1
-  LEAD_MHP_SELECTION = 3
-
-  FCW_THRESHOLD_5MS2_HIGH = 0.15
-  FCW_THRESHOLD_5MS2_LOW = 0.05
-  FCW_THRESHOLD_3MS2 = 0.7
-
-  CONFIDENCE_BUFFER_LEN = 5
-  RYG_GREEN = 0.01165
-  RYG_YELLOW = 0.06157
-
-  POLY_PATH_DEGREE = 4
-
-
-# model outputs slices
-class Plan:
-  POSITION = slice(0, 3)
-  VELOCITY = slice(3, 6)
-  ACCELERATION = slice(6, 9)
-  T_FROM_CURRENT_EULER = slice(9, 12)
-  ORIENTATION_RATE = slice(12, 15)
-
-
-class Meta:
-  ENGAGED = slice(0, 1)
-  # next 2, 4, 6, 8, 10 seconds
-  GAS_DISENGAGE = slice(1, 31, 6)
-  BRAKE_DISENGAGE = slice(2, 31, 6)
-  STEER_OVERRIDE = slice(3, 31, 6)
-  HARD_BRAKE_3 = slice(4, 31, 6)
-  HARD_BRAKE_4 = slice(5, 31, 6)
-  HARD_BRAKE_5 = slice(6, 31, 6)
-  # next 0, 2, 4, 6, 8, 10 seconds
-  GAS_PRESS = slice(31, 55, 4)
-  BRAKE_PRESS = slice(32, 55, 4)
-  LEFT_BLINKER = slice(33, 55, 4)
-  RIGHT_BLINKER = slice(34, 55, 4)
-
-
-class MetaTombRaider:
-  ENGAGED = slice(0, 1)
-  # next 2, 4, 6, 8, 10 seconds
-  GAS_DISENGAGE = slice(1, 41, 8)
-  BRAKE_DISENGAGE = slice(2, 41, 8)
-  STEER_OVERRIDE = slice(3, 41, 8)
-  HARD_BRAKE_3 = slice(4, 41, 8)
-  HARD_BRAKE_4 = slice(5, 41, 8)
-  HARD_BRAKE_5 = slice(6, 41, 8)
-  GAS_PRESS = slice(7, 41, 8)
-  BRAKE_PRESS = slice(8, 41, 8)
-  # next 0, 2, 4, 6, 8, 10 seconds
-  LEFT_BLINKER = slice(41, 53, 2)
-  RIGHT_BLINKER = slice(42, 53, 2)
-
-
-class MetaSimPose:
-  ENGAGED = slice(0, 1)
-  # next 2, 4, 6, 8, 10 seconds
-  GAS_DISENGAGE = slice(1, 36, 7)
-  BRAKE_DISENGAGE = slice(2, 36, 7)
-  STEER_OVERRIDE = slice(3, 36, 7)
-  HARD_BRAKE_3 = slice(4, 36, 7)
-  HARD_BRAKE_4 = slice(5, 36, 7)
-  HARD_BRAKE_5 = slice(6, 36, 7)
-  GAS_PRESS = slice(7, 36, 7)
-  # next 0, 2, 4, 6, 8, 10 seconds
-  LEFT_BLINKER = slice(36, 48, 2)
-  RIGHT_BLINKER = slice(37, 48, 2)
diff --git a/openpilot/sunnypilot/models/fetcher.py b/openpilot/sunnypilot/models/fetcher.py
index 810b9b7e49..16fa378c4e 100644
--- a/openpilot/sunnypilot/models/fetcher.py
+++ b/openpilot/sunnypilot/models/fetcher.py
@@ -139,7 +139,7 @@ class ModelCache:
 class ModelFetcher:
   """Handles fetching and caching of model data from remote source"""
   MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v22.json"
-  MODEL_URL_CHESTNUT = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_chestnut_v24.json"
+  MODEL_URL_CHESTNUT = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_chestnut_v25.json"
 
   MODEL_SOURCES = {
     "qcom": (MODEL_URL, ""),
diff --git a/openpilot/sunnypilot/models/helpers.py b/openpilot/sunnypilot/models/helpers.py
index ac69096597..a1a392c5ee 100644
--- a/openpilot/sunnypilot/models/helpers.py
+++ b/openpilot/sunnypilot/models/helpers.py
@@ -7,14 +7,11 @@ See the LICENSE.md file in the root directory for more details.
 
 import hashlib
 import os
-import pickle
-from pathlib import Path
 import numpy as np
 
 from openpilot.cereal import custom
 from openpilot.common.params import Params
 from openpilot.common.swaglog import cloudlog
-from openpilot.sunnypilot.models.constants import Meta, MetaSimPose, MetaTombRaider
 from openpilot.common.hardware.hw import Paths
 from openpilot.selfdrive.modeld.helpers import chestnut_present
 
@@ -22,7 +19,6 @@ from openpilot.selfdrive.modeld.helpers import chestnut_present
 REQUIRED_JSON_VERSION = 19
 
 CUSTOM_MODEL_PATH = Paths.model_root()
-METADATA_PATH = Path(__file__).parent / '../models/supercombo_metadata.pkl'
 ModelManager = custom.ModelManagerSP
 
 ACTIVE_BUNDLE_KEYS = {
@@ -201,33 +197,6 @@ def _get_model():
   return None
 
 
-def load_metadata():
-  metadata_path = METADATA_PATH
-
-  with open(metadata_path, 'rb') as f:
-    return pickle.load(f)
-
-
-def prepare_inputs(model_metadata: dict) -> dict[str, np.ndarray]:
-  return {
-    key: np.zeros(shape, dtype=np.float32).flatten()
-    for key, shape in model_metadata['input_shapes'].items()
-    if 'img' not in key
-  }
-
-
-def load_meta_constants(model_metadata: dict):
-  """ Loads the appropriate meta model class based on key shapes"""
-  if 'sim_pose' in model_metadata['input_shapes']:
-    return MetaSimPose
-
-  meta_slice = model_metadata['output_slices']['meta']
-  if (meta_slice.start, meta_slice.stop, meta_slice.step) == (5868, 5921, None):
-    return MetaTombRaider
-
-  return Meta
-
-
 # The following method(s) are modeld helper methods
 def plan_x_idxs_helper(constants, plan, model_output) -> list[float]:
   # times at X_IDXS according to plan.