diff --git a/cereal/custom.capnp b/cereal/custom.capnp
index b75983e9a..3aa9c7ad1 100644
--- a/cereal/custom.capnp
+++ b/cereal/custom.capnp
@@ -81,6 +81,7 @@ struct ModelManagerSP @0xaedffd8f31e7b55d {
     generation @5 :UInt32;
     environment @6 :Text;
     runner @7 :Runner;
+    is20hz @8 :Bool;
   }
 }
 
diff --git a/selfdrive/modeld/__init__.py b/selfdrive/modeld/__init__.py
index e69de29bb..639622e82 100644
--- a/selfdrive/modeld/__init__.py
+++ b/selfdrive/modeld/__init__.py
@@ -0,0 +1,5 @@
+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/selfdrive/modeld/fill_model_msg.py b/selfdrive/modeld/fill_model_msg.py
index 3056da937..3f5bf2f27 100644
--- a/selfdrive/modeld/fill_model_msg.py
+++ b/selfdrive/modeld/fill_model_msg.py
@@ -2,13 +2,33 @@ import os
 import capnp
 import numpy as np
 from cereal import log
-from openpilot.selfdrive.modeld.constants import ModelConstants, Plan, Meta
+from openpilot.selfdrive.modeld.constants import ModelConstants, Plan
+from openpilot.selfdrive.controls.lib.drive_helpers import MIN_SPEED
 
 SEND_RAW_PRED = os.getenv('SEND_RAW_PRED')
 
 ConfidenceClass = log.ModelDataV2.ConfidenceClass
 
 
+def curv_from_psis(psi_target, psi_rate, vego, delay):
+  vego = np.clip(vego, MIN_SPEED, np.inf)
+  curv_from_psi = psi_target / (vego * delay)  # epsilon to prevent divide-by-zero
+  return 2 * curv_from_psi - psi_rate / vego
+
+
+def get_curvature_from_plan(plan, vego, delay):
+  psi_target = np.interp(delay, ModelConstants.T_IDXS, plan[:, Plan.T_FROM_CURRENT_EULER][:, 2])
+  psi_rate = plan[:, Plan.ORIENTATION_RATE][0, 2]
+  return curv_from_psis(psi_target, psi_rate, vego, delay)
+
+
+def get_curvature_from_output(output, vego, delay):
+  if desired_curv := output.get('desired_curvature'):  # If the model outputs the desired curvature, use that directly
+    return float(desired_curv[0, 0])
+
+  return float(get_curvature_from_plan(output['plan'][0], vego, delay))
+
+
 class PublishState:
   def __init__(self):
     self.disengage_buffer = np.zeros(ModelConstants.CONFIDENCE_BUFFER_LEN*ModelConstants.DISENGAGE_WIDTH, dtype=np.float32)
@@ -59,12 +79,14 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
                    net_output_data: dict[str, np.ndarray], v_ego: float, delay: float,
                    publish_state: PublishState, vipc_frame_id: int, vipc_frame_id_extra: int,
                    frame_id: int, frame_drop: float, timestamp_eof: int, model_execution_time: float,
-                   valid: bool) -> None:
+                   valid: bool, model_meta) -> None:
   frame_age = frame_id - vipc_frame_id if frame_id > vipc_frame_id else 0
   frame_drop_perc = frame_drop * 100
   extended_msg.valid = valid
   base_msg.valid = valid
 
+  desired_curvature = float(get_curvature_from_output(net_output_data, v_ego, delay))
+
   driving_model_data = base_msg.drivingModelData
 
   driving_model_data.frameId = vipc_frame_id
@@ -73,7 +95,7 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
   driving_model_data.modelExecutionTime = model_execution_time
 
   action = driving_model_data.action
-  action.desiredCurvature = float(net_output_data['desired_curvature'][0,0])
+  action.desiredCurvature = desired_curvature
 
   modelV2 = extended_msg.modelV2
   modelV2.frameId = vipc_frame_id
@@ -108,7 +130,7 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
 
   # lateral planning
   action = modelV2.action
-  action.desiredCurvature = float(net_output_data['desired_curvature'][0,0])
+  action.desiredCurvature = desired_curvature
 
   # times at X_IDXS according to model plan
   PLAN_T_IDXS = [np.nan] * ModelConstants.IDX_N
@@ -159,23 +181,25 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
   meta = modelV2.meta
   meta.desireState = net_output_data['desire_state'][0].reshape(-1).tolist()
   meta.desirePrediction = net_output_data['desire_pred'][0].reshape(-1).tolist()
-  meta.engagedProb = net_output_data['meta'][0,Meta.ENGAGED].item()
+  meta.engagedProb = net_output_data['meta'][0,model_meta.ENGAGED].item()
   meta.init('disengagePredictions')
   disengage_predictions = meta.disengagePredictions
   disengage_predictions.t = ModelConstants.META_T_IDXS
-  disengage_predictions.brakeDisengageProbs = net_output_data['meta'][0,Meta.BRAKE_DISENGAGE].tolist()
-  disengage_predictions.gasDisengageProbs = net_output_data['meta'][0,Meta.GAS_DISENGAGE].tolist()
-  disengage_predictions.steerOverrideProbs = net_output_data['meta'][0,Meta.STEER_OVERRIDE].tolist()
-  disengage_predictions.brake3MetersPerSecondSquaredProbs = net_output_data['meta'][0,Meta.HARD_BRAKE_3].tolist()
-  disengage_predictions.brake4MetersPerSecondSquaredProbs = net_output_data['meta'][0,Meta.HARD_BRAKE_4].tolist()
-  disengage_predictions.brake5MetersPerSecondSquaredProbs = net_output_data['meta'][0,Meta.HARD_BRAKE_5].tolist()
-  #disengage_predictions.gasPressProbs = net_output_data['meta'][0,Meta.GAS_PRESS].tolist()
-  #disengage_predictions.brakePressProbs = net_output_data['meta'][0,Meta.BRAKE_PRESS].tolist()
+  disengage_predictions.brakeDisengageProbs = net_output_data['meta'][0,model_meta.BRAKE_DISENGAGE].tolist()
+  disengage_predictions.gasDisengageProbs = net_output_data['meta'][0,model_meta.GAS_DISENGAGE].tolist()
+  disengage_predictions.steerOverrideProbs = net_output_data['meta'][0,model_meta.STEER_OVERRIDE].tolist()
+  disengage_predictions.brake3MetersPerSecondSquaredProbs = net_output_data['meta'][0,model_meta.HARD_BRAKE_3].tolist()
+  disengage_predictions.brake4MetersPerSecondSquaredProbs = net_output_data['meta'][0,model_meta.HARD_BRAKE_4].tolist()
+  disengage_predictions.brake5MetersPerSecondSquaredProbs = net_output_data['meta'][0,model_meta.HARD_BRAKE_5].tolist()
+
+  if hasattr(model_meta, 'GAS_PRESS') and hasattr(model_meta, 'BRAKE_PRESS'):
+    disengage_predictions.gasPressProbs = net_output_data['meta'][0,model_meta.GAS_PRESS].tolist()
+    disengage_predictions.brakePressProbs = net_output_data['meta'][0,model_meta.BRAKE_PRESS].tolist()
 
   publish_state.prev_brake_5ms2_probs[:-1] = publish_state.prev_brake_5ms2_probs[1:]
-  publish_state.prev_brake_5ms2_probs[-1] = net_output_data['meta'][0,Meta.HARD_BRAKE_5][0]
+  publish_state.prev_brake_5ms2_probs[-1] = net_output_data['meta'][0,model_meta.HARD_BRAKE_5][0]
   publish_state.prev_brake_3ms2_probs[:-1] = publish_state.prev_brake_3ms2_probs[1:]
-  publish_state.prev_brake_3ms2_probs[-1] = net_output_data['meta'][0,Meta.HARD_BRAKE_3][0]
+  publish_state.prev_brake_3ms2_probs[-1] = net_output_data['meta'][0,model_meta.HARD_BRAKE_3][0]
   hard_brake_predicted = (publish_state.prev_brake_5ms2_probs > ModelConstants.FCW_THRESHOLDS_5MS2).all() and \
     (publish_state.prev_brake_3ms2_probs > ModelConstants.FCW_THRESHOLDS_3MS2).all()
   meta.hardBrakePredicted = hard_brake_predicted.item()
@@ -183,9 +207,9 @@ def fill_model_msg(base_msg: capnp._DynamicStructBuilder, extended_msg: capnp._D
   # confidence
   if vipc_frame_id % (2*ModelConstants.MODEL_FREQ) == 0:
     # any disengage prob
-    brake_disengage_probs = net_output_data['meta'][0,Meta.BRAKE_DISENGAGE]
-    gas_disengage_probs = net_output_data['meta'][0,Meta.GAS_DISENGAGE]
-    steer_override_probs = net_output_data['meta'][0,Meta.STEER_OVERRIDE]
+    brake_disengage_probs = net_output_data['meta'][0,model_meta.BRAKE_DISENGAGE]
+    gas_disengage_probs = net_output_data['meta'][0,model_meta.GAS_DISENGAGE]
+    steer_override_probs = net_output_data['meta'][0,model_meta.STEER_OVERRIDE]
     any_disengage_probs = 1-((1-brake_disengage_probs)*(1-gas_disengage_probs)*(1-steer_override_probs))
     # independent disengage prob for each 2s slice
     ind_disengage_probs = np.r_[any_disengage_probs[0], np.diff(any_disengage_probs) / (1 - any_disengage_probs[:-1])]
diff --git a/selfdrive/modeld/modeld.py b/selfdrive/modeld/modeld.py
index 5783f6aa8..3d7e385d6 100755
--- a/selfdrive/modeld/modeld.py
+++ b/selfdrive/modeld/modeld.py
@@ -1,21 +1,11 @@
 #!/usr/bin/env python3
-import os
 from openpilot.system.hardware import TICI
 
 #
-if TICI:
-  from tinygrad.tensor import Tensor
-  from tinygrad.dtype import dtypes
-  from openpilot.selfdrive.modeld.runners.tinygrad_helpers import qcom_tensor_from_opencl_address
-  os.environ['QCOM'] = '1'
-else:
-  from openpilot.selfdrive.modeld.runners.ort_helpers import make_onnx_cpu_runner
 import time
-import pickle
 import numpy as np
 import cereal.messaging as messaging
 from cereal import car, log
-from pathlib import Path
 from setproctitle import setproctitle
 from cereal.messaging import PubMaster, SubMaster
 from msgq.visionipc import VisionIpcClient, VisionStreamType, VisionBuf
@@ -33,13 +23,11 @@ from openpilot.selfdrive.modeld.fill_model_msg import fill_model_msg, fill_pose_
 from openpilot.selfdrive.modeld.constants import ModelConstants
 from openpilot.selfdrive.modeld.models.commonmodel_pyx import DrivingModelFrame, CLContext
 
+from openpilot.sunnypilot.modeld_v2.meta_helper import load_meta_constants
+from openpilot.sunnypilot.modeld_v2.model_runner import ONNXRunner, TinygradRunner
 
 PROCESS_NAME = "selfdrive.modeld.modeld"
-SEND_RAW_PRED = os.getenv('SEND_RAW_PRED')
 
-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'
 
 class FrameMeta:
   frame_id: int = 0
@@ -57,39 +45,35 @@ class ModelState:
   prev_desire: np.ndarray  # for tracking the rising edge of the pulse
 
   def __init__(self, context: CLContext):
-    self.frames = {'input_imgs': DrivingModelFrame(context), 'big_input_imgs': DrivingModelFrame(context)}
+    try:
+      self.model_runner = TinygradRunner() if TICI else ONNXRunner()
+    except Exception as e:
+      cloudlog.exception(f"Failed to initialize model runner: {str(e)}")
+
+    buffer_length = 5 if self.model_runner.is_20hz else 2
+    self.frames = {'input_imgs': DrivingModelFrame(context, buffer_length), 'big_input_imgs': DrivingModelFrame(context, buffer_length)}
     self.prev_desire = np.zeros(ModelConstants.DESIRE_LEN, dtype=np.float32)
+    if self.model_runner.is_20hz:
+      self.full_features_20Hz = np.zeros((ModelConstants.FULL_HISTORY_BUFFER_LEN, ModelConstants.FEATURE_LEN), dtype=np.float32)
+      self.desire_20Hz = np.zeros((ModelConstants.FULL_HISTORY_BUFFER_LEN + 1, ModelConstants.DESIRE_LEN), dtype=np.float32)
 
     # img buffers are managed in openCL transform code
-    self.numpy_inputs = {
-      'desire': np.zeros((1, (ModelConstants.FULL_HISTORY_BUFFER_LEN+1), ModelConstants.DESIRE_LEN), dtype=np.float32),
-      'traffic_convention': np.zeros((1, ModelConstants.TRAFFIC_CONVENTION_LEN), dtype=np.float32),
-      'lateral_control_params': np.zeros((1, ModelConstants.LATERAL_CONTROL_PARAMS_LEN), dtype=np.float32),
-      'prev_desired_curv': np.zeros((1, (ModelConstants.FULL_HISTORY_BUFFER_LEN+1), ModelConstants.PREV_DESIRED_CURV_LEN), dtype=np.float32),
-      'features_buffer': np.zeros((1, ModelConstants.FULL_HISTORY_BUFFER_LEN,  ModelConstants.FEATURE_LEN), dtype=np.float32),
-    }
+    self.numpy_inputs = {}
 
-    with open(METADATA_PATH, 'rb') as f:
-      model_metadata = pickle.load(f)
-    self.input_shapes =  model_metadata['input_shapes']
+    for key, shape in self.model_runner.input_shapes.items():
+      if key not in self.frames: # Managed by opencl
+        self.numpy_inputs[key] = np.zeros(shape, dtype=np.float32)
 
-    self.output_slices = model_metadata['output_slices']
-    net_output_size = model_metadata['output_shapes']['outputs'][1]
-    self.output = np.zeros(net_output_size, dtype=np.float32)
     self.parser = Parser()
 
-    if TICI:
-      self.tensor_inputs = {k: Tensor(v, device='NPY').realize() for k,v in self.numpy_inputs.items()}
-      with open(MODEL_PKL_PATH, "rb") as f:
-        self.model_run = pickle.load(f)
-    else:
-      self.onnx_cpu_runner = make_onnx_cpu_runner(MODEL_PATH)
+    if self.model_runner.is_20hz:
+      net_output_size = self.model_runner.model_metadata['output_shapes']['outputs'][1]
+      self.output = np.zeros(net_output_size, dtype=np.float32)
 
-  def slice_outputs(self, model_outputs: np.ndarray) -> dict[str, np.ndarray]:
-    parsed_model_outputs = {k: model_outputs[np.newaxis, v] for k,v in self.output_slices.items()}
-    if SEND_RAW_PRED:
-      parsed_model_outputs['raw_pred'] = model_outputs.copy()
-    return parsed_model_outputs
+      num_elements = self.numpy_inputs['features_buffer'].shape[1]
+      step_size = int(-100 / num_elements)
+      self.full_features_20Hz_idxs = np.arange(step_size, step_size * (num_elements + 1), step_size)[::-1]
+      self.desire_reshape_dims = (self.numpy_inputs['desire'].shape[0], self.numpy_inputs['desire'].shape[1], -1, self.numpy_inputs['desire'].shape[2])
 
   def run(self, buf: VisionBuf, wbuf: VisionBuf, transform: np.ndarray, transform_wide: np.ndarray,
                 inputs: dict[str, np.ndarray], prepare_only: bool) -> dict[str, np.ndarray] | None:
@@ -98,40 +82,53 @@ class ModelState:
     new_desire = np.where(inputs['desire'] - self.prev_desire > .99, inputs['desire'], 0)
     self.prev_desire[:] = inputs['desire']
 
-    self.numpy_inputs['desire'][0,:-1] = self.numpy_inputs['desire'][0,1:]
-    self.numpy_inputs['desire'][0,-1] = new_desire
+    if self.model_runner.is_20hz:
+      self.desire_20Hz[:-1] = self.desire_20Hz[1:]
+      self.desire_20Hz[-1] = new_desire
+      self.numpy_inputs['desire'][:] = self.desire_20Hz.reshape(self.desire_reshape_dims).max(axis=2)
+    else:
+      length = inputs['desire'].shape[0]
+      self.numpy_inputs['desire'][0, :-1] = self.numpy_inputs['desire'][0, 1:]
+      self.numpy_inputs['desire'][0, -1, :length] = new_desire[:length]
+
+    for key in self.numpy_inputs:
+      if key in inputs and key not in ['desire']:
+        self.numpy_inputs[key][:] = inputs[key]
 
-    self.numpy_inputs['traffic_convention'][:] = inputs['traffic_convention']
-    self.numpy_inputs['lateral_control_params'][:] = inputs['lateral_control_params']
     imgs_cl = {'input_imgs': self.frames['input_imgs'].prepare(buf, transform.flatten()),
                'big_input_imgs': self.frames['big_input_imgs'].prepare(wbuf, transform_wide.flatten())}
 
-    if TICI:
-      # The imgs tensors are backed by opencl memory, only need init once
-      for key in imgs_cl:
-        if key not in self.tensor_inputs:
-          self.tensor_inputs[key] = qcom_tensor_from_opencl_address(imgs_cl[key].mem_address, self.input_shapes[key], dtype=dtypes.uint8)
-    else:
-      for key in imgs_cl:
-        self.numpy_inputs[key] = self.frames[key].buffer_from_cl(imgs_cl[key]).reshape(self.input_shapes[key]).astype(dtype=np.float32)
+    # Prepare inputs using the model runner
+    self.model_runner.prepare_inputs(imgs_cl, self.numpy_inputs, self.frames)
 
     if prepare_only:
       return None
 
-    if TICI:
-      self.output = self.model_run(**self.tensor_inputs).numpy().flatten()
+    # Run model inference
+    self.output = self.model_runner.run_model()
+    outputs = self.parser.parse_outputs(self.model_runner.slice_outputs(self.output))
+
+    if self.model_runner.is_20hz:
+      self.full_features_20Hz[:-1] = self.full_features_20Hz[1:]
+      self.full_features_20Hz[-1] = outputs['hidden_state'][0, :]
+      self.numpy_inputs['features_buffer'][:] = self.full_features_20Hz[self.full_features_20Hz_idxs]
     else:
-      self.output = self.onnx_cpu_runner.run(None, self.numpy_inputs)[0].flatten()
+      feature_len = outputs['hidden_state'].shape[1]
+      self.numpy_inputs['features_buffer'][0, :-1] = self.numpy_inputs['features_buffer'][0, 1:]
+      self.numpy_inputs['features_buffer'][0, -1, :feature_len] = outputs['hidden_state'][0, :feature_len]
 
-    outputs = self.parser.parse_outputs(self.slice_outputs(self.output))
+    if "desired_curvature" in outputs:
+      input_name_prev = None
 
-    self.numpy_inputs['features_buffer'][0,:-1] = self.numpy_inputs['features_buffer'][0,1:]
-    self.numpy_inputs['features_buffer'][0,-1] = outputs['hidden_state'][0, :]
+      if "prev_desired_curvs" in self.numpy_inputs.keys():
+        input_name_prev = 'prev_desired_curvs'
+      elif "prev_desired_curv" in self.numpy_inputs.keys():
+        input_name_prev = 'prev_desired_curv'
 
-
-    # TODO model only uses last value now
-    self.numpy_inputs['prev_desired_curv'][0,:-1] = self.numpy_inputs['prev_desired_curv'][0,1:]
-    self.numpy_inputs['prev_desired_curv'][0,-1,:] = outputs['desired_curvature'][0, :]
+      if input_name_prev is not None:
+        length = outputs['desired_curvature'][0].size
+        self.numpy_inputs[input_name_prev][0, :-length, 0] = self.numpy_inputs[input_name_prev][0, length:, 0]
+        self.numpy_inputs[input_name_prev][0, -length:, 0] = outputs['desired_curvature'][0]
     return outputs
 
 
@@ -242,7 +239,6 @@ def main(demo=False):
     is_rhd = sm["driverMonitoringState"].isRHD
     frame_id = sm["roadCameraState"].frameId
     v_ego = max(sm["carState"].vEgo, 0.)
-    lateral_control_params = np.array([v_ego, steer_delay], dtype=np.float32)
     if sm.updated["liveCalibration"] and sm.seen['roadCameraState'] and sm.seen['deviceState']:
       device_from_calib_euler = np.array(sm["liveCalibration"].rpyCalib, dtype=np.float32)
       dc = DEVICE_CAMERAS[(str(sm['deviceState'].deviceType), str(sm['roadCameraState'].sensor))]
@@ -273,8 +269,10 @@ def main(demo=False):
     inputs:dict[str, np.ndarray] = {
       'desire': vec_desire,
       'traffic_convention': traffic_convention,
-      'lateral_control_params': lateral_control_params,
-      }
+    }
+
+    if "lateral_control_params" in model.numpy_inputs.keys():
+      inputs['lateral_control_params'] = np.array([v_ego, steer_delay], dtype=np.float32)
 
     mt1 = time.perf_counter()
     model_output = model.run(buf_main, buf_extra, model_transform_main, model_transform_extra, inputs, prepare_only)
@@ -287,7 +285,7 @@ def main(demo=False):
       posenet_send = messaging.new_message('cameraOdometry')
       fill_model_msg(drivingdata_send, modelv2_send, model_output, v_ego, steer_delay,
                      publish_state, meta_main.frame_id, meta_extra.frame_id, frame_id,
-                     frame_drop_ratio, meta_main.timestamp_eof, model_execution_time, live_calib_seen)
+                     frame_drop_ratio, meta_main.timestamp_eof, model_execution_time, live_calib_seen, load_meta_constants())
 
       desire_state = modelv2_send.modelV2.meta.desireState
       l_lane_change_prob = desire_state[log.Desire.laneChangeLeft]
diff --git a/selfdrive/modeld/models/commonmodel.cc b/selfdrive/modeld/models/commonmodel.cc
index 9973d1858..399836b0c 100644
--- a/selfdrive/modeld/models/commonmodel.cc
+++ b/selfdrive/modeld/models/commonmodel.cc
@@ -5,13 +5,14 @@
 
 #include "common/clutil.h"
 
-DrivingModelFrame::DrivingModelFrame(cl_device_id device_id, cl_context context) : ModelFrame(device_id, context) {
+DrivingModelFrame::DrivingModelFrame(cl_device_id device_id, cl_context context, uint8_t buffer_length) : ModelFrame(device_id, context), buffer_length(buffer_length) {
   input_frames = std::make_unique<uint8_t[]>(buf_size);
   input_frames_cl = CL_CHECK_ERR(clCreateBuffer(context, CL_MEM_READ_WRITE, buf_size, NULL, &err));
-  img_buffer_20hz_cl = CL_CHECK_ERR(clCreateBuffer(context, CL_MEM_READ_WRITE, 2*frame_size_bytes, NULL, &err));
-  region.origin = 1 * frame_size_bytes;
+  img_buffer_20hz_cl = CL_CHECK_ERR(clCreateBuffer(context, CL_MEM_READ_WRITE, buffer_length*frame_size_bytes, NULL, &err));
+  region.origin = (buffer_length - 1)  * frame_size_bytes;
   region.size = frame_size_bytes;
   last_img_cl = CL_CHECK_ERR(clCreateSubBuffer(img_buffer_20hz_cl, CL_MEM_READ_WRITE, CL_BUFFER_CREATE_TYPE_REGION, &region, &err));
+  // printf("Buffer length: %d, region origin: %lu, region size: %lu\n", buffer_length, region.origin, region.size);
 
   loadyuv_init(&loadyuv, context, device_id, MODEL_WIDTH, MODEL_HEIGHT);
   init_transform(device_id, context, MODEL_WIDTH, MODEL_HEIGHT);
@@ -20,7 +21,7 @@ DrivingModelFrame::DrivingModelFrame(cl_device_id device_id, cl_context context)
 cl_mem* DrivingModelFrame::prepare(cl_mem yuv_cl, int frame_width, int frame_height, int frame_stride, int frame_uv_offset, const mat3& projection) {
   run_transform(yuv_cl, MODEL_WIDTH, MODEL_HEIGHT, frame_width, frame_height, frame_stride, frame_uv_offset, projection);
 
-  for (int i = 0; i < 1; i++) {
+  for (int i = 0; i < (buffer_length - 1); i++) {
     CL_CHECK(clEnqueueCopyBuffer(q, img_buffer_20hz_cl, img_buffer_20hz_cl, (i+1)*frame_size_bytes, i*frame_size_bytes, frame_size_bytes, 0, nullptr, nullptr));
   }
   loadyuv_queue(&loadyuv, q, y_cl, u_cl, v_cl, last_img_cl);
diff --git a/selfdrive/modeld/models/commonmodel.h b/selfdrive/modeld/models/commonmodel.h
index 14409943e..3b5db05c7 100644
--- a/selfdrive/modeld/models/commonmodel.h
+++ b/selfdrive/modeld/models/commonmodel.h
@@ -64,7 +64,7 @@ protected:
 
 class DrivingModelFrame : public ModelFrame {
 public:
-  DrivingModelFrame(cl_device_id device_id, cl_context context);
+  DrivingModelFrame(cl_device_id device_id, cl_context context, uint8_t buffer_length);
   ~DrivingModelFrame();
   cl_mem* prepare(cl_mem yuv_cl, int frame_width, int frame_height, int frame_stride, int frame_uv_offset, const mat3& projection);
 
@@ -73,6 +73,7 @@ public:
   const int MODEL_FRAME_SIZE = MODEL_WIDTH * MODEL_HEIGHT * 3 / 2;
   const int buf_size = MODEL_FRAME_SIZE * 2;
   const size_t frame_size_bytes = MODEL_FRAME_SIZE * sizeof(uint8_t);
+  const uint8_t buffer_length;
 
 private:
   LoadYUVState loadyuv;
diff --git a/selfdrive/modeld/models/commonmodel.pxd b/selfdrive/modeld/models/commonmodel.pxd
index b4f08b12a..f640597b8 100644
--- a/selfdrive/modeld/models/commonmodel.pxd
+++ b/selfdrive/modeld/models/commonmodel.pxd
@@ -20,7 +20,7 @@ cdef extern from "selfdrive/modeld/models/commonmodel.h":
 
   cppclass DrivingModelFrame:
     int buf_size
-    DrivingModelFrame(cl_device_id, cl_context)
+    DrivingModelFrame(cl_device_id, cl_context, unsigned char)
 
   cppclass MonitoringModelFrame:
     int buf_size
diff --git a/selfdrive/modeld/models/commonmodel_pyx.pyx b/selfdrive/modeld/models/commonmodel_pyx.pyx
index 7b3a5bb34..78a891f03 100644
--- a/selfdrive/modeld/models/commonmodel_pyx.pyx
+++ b/selfdrive/modeld/models/commonmodel_pyx.pyx
@@ -4,7 +4,7 @@
 import numpy as np
 cimport numpy as cnp
 from libc.string cimport memcpy
-from libc.stdint cimport uintptr_t
+from libc.stdint cimport uintptr_t, uint8_t
 
 from msgq.visionipc.visionipc cimport cl_mem
 from msgq.visionipc.visionipc_pyx cimport VisionBuf, CLContext as BaseCLContext
@@ -59,8 +59,8 @@ cdef class ModelFrame:
 cdef class DrivingModelFrame(ModelFrame):
   cdef cppDrivingModelFrame * _frame
 
-  def __cinit__(self, CLContext context):
-    self._frame = new cppDrivingModelFrame(context.device_id, context.context)
+  def __cinit__(self, CLContext context, int buffer_length=2):
+    self._frame = new cppDrivingModelFrame(context.device_id, context.context, buffer_length)
     self.frame = <cppModelFrame*>(self._frame)
     self.buf_size = self._frame.buf_size
 
diff --git a/sunnypilot/modeld_v2/__init__.py b/sunnypilot/modeld_v2/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/sunnypilot/modeld_v2/meta_20hz.py b/sunnypilot/modeld_v2/meta_20hz.py
new file mode 100644
index 000000000..77a815ee8
--- /dev/null
+++ b/sunnypilot/modeld_v2/meta_20hz.py
@@ -0,0 +1,17 @@
+from openpilot.selfdrive.modeld.constants import Meta
+
+
+class Meta20hz(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)
diff --git a/sunnypilot/modeld_v2/meta_helper.py b/sunnypilot/modeld_v2/meta_helper.py
new file mode 100644
index 000000000..b9c6b98c9
--- /dev/null
+++ b/sunnypilot/modeld_v2/meta_helper.py
@@ -0,0 +1,26 @@
+from openpilot.selfdrive.modeld.constants import Meta
+from 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
diff --git a/sunnypilot/modeld_v2/model_runner.py b/sunnypilot/modeld_v2/model_runner.py
new file mode 100644
index 000000000..500a34a4e
--- /dev/null
+++ b/sunnypilot/modeld_v2/model_runner.py
@@ -0,0 +1,134 @@
+import os
+import pickle
+from abc import ABC, abstractmethod
+import numpy as np
+
+from cereal import custom
+from openpilot.selfdrive.modeld import MODEL_PATH, MODEL_PKL_PATH, METADATA_PATH
+from openpilot.selfdrive.modeld.models.commonmodel_pyx import DrivingModelFrame, CLMem
+from openpilot.selfdrive.modeld.runners.ort_helpers import make_onnx_cpu_runner, ORT_TYPES_TO_NP_TYPES
+from openpilot.selfdrive.modeld.runners.tinygrad_helpers import qcom_tensor_from_opencl_address
+from openpilot.system.hardware import TICI
+from openpilot.system.hardware.hw import Paths
+
+from openpilot.sunnypilot.models.helpers import get_active_bundle
+from tinygrad.tensor import Tensor
+
+if TICI:
+  os.environ['QCOM'] = '1'
+
+SEND_RAW_PRED = os.getenv('SEND_RAW_PRED')
+CUSTOM_MODEL_PATH = Paths.model_root()
+ModelManager = custom.ModelManagerSP
+
+
+class ModelRunner(ABC):
+  """Abstract base class for model runners that defines the interface for running ML models."""
+
+  def __init__(self):
+    """Initialize the model runner with paths to model and metadata files."""
+    metadata_path = METADATA_PATH
+    self.is_20hz = None
+    self._drive_model = None
+    self._metadata_model = None
+
+    if bundle := get_active_bundle():
+      bundle_models = {model.type.raw: model for model in bundle.models}
+      self._drive_model = bundle_models.get(ModelManager.Type.drive)
+      self._metadata_model = bundle_models.get(ModelManager.Type.metadata)
+      self.is_20hz = bundle.is20hz
+
+    # Override the metadata path if a metadata model is found in the active bundle
+    if self._metadata_model:
+      metadata_path = f"{CUSTOM_MODEL_PATH}/{self._metadata_model.fileName}"
+
+    with open(metadata_path, 'rb') as f:
+      self.model_metadata = pickle.load(f)
+
+    self.input_shapes = self.model_metadata['input_shapes']
+    self.output_slices = self.model_metadata['output_slices']
+    self.inputs: dict = {}
+
+  @abstractmethod
+  def prepare_inputs(self, imgs_cl: dict[str, CLMem], numpy_inputs: dict[str, np.ndarray], frames: dict[str, DrivingModelFrame]) -> dict:
+    """Prepare inputs for model inference."""
+    raise NotImplementedError
+
+  @abstractmethod
+  def run_model(self):
+    """Run model inference with prepared inputs."""
+
+  def slice_outputs(self, model_outputs: np.ndarray) -> dict:
+    """Slice model outputs according to metadata configuration."""
+    parsed_outputs = {k: model_outputs[np.newaxis, v] for k, v in self.output_slices.items()}
+    if SEND_RAW_PRED:
+      parsed_outputs['raw_pred'] = model_outputs.copy()
+    return parsed_outputs
+
+
+class TinygradRunner(ModelRunner):
+  """Tinygrad implementation of model runner for TICI hardware."""
+
+  def __init__(self):
+    super().__init__()
+
+    model_pkl_path = MODEL_PKL_PATH
+    if self._drive_model:
+      model_pkl_path = f"{CUSTOM_MODEL_PATH}/{self._drive_model.fileName}"
+      assert model_pkl_path.endswith('_tinygrad.pkl'), f"Invalid model file: {model_pkl_path} for TinygradRunner"
+
+    # Load Tinygrad model
+    with open(model_pkl_path, "rb") as f:
+      try:
+        self.model_run = pickle.load(f)
+      except FileNotFoundError as e:
+        assert "/dev/kgsl-3d0" not in str(e), "Model was built on C3 or C3X, but is being loaded on PC"
+        raise
+
+    self.input_to_dtype = {}
+    self.input_to_device = {}
+
+    for idx, name in enumerate(self.model_run.captured.expected_names):
+      self.input_to_dtype[name] = self.model_run.captured.expected_st_vars_dtype_device[idx][2]  # 2 is the dtype
+      self.input_to_device[name] = self.model_run.captured.expected_st_vars_dtype_device[idx][3]  # 3 is the device
+
+  def prepare_inputs(self, imgs_cl: dict[str, CLMem], numpy_inputs: dict[str, np.ndarray], frames: dict[str, DrivingModelFrame]) -> dict:
+    # Initialize image tensors if not already done
+    for key in imgs_cl:
+      if TICI and key not in self.inputs:
+        self.inputs[key] = qcom_tensor_from_opencl_address(imgs_cl[key].mem_address, self.input_shapes[key], dtype=self.input_to_dtype[key])
+      elif not TICI:
+        shape = frames[key].buffer_from_cl(imgs_cl[key]).reshape(self.input_shapes[key])
+        self.inputs[key] = Tensor(shape, device=self.input_to_device[key], dtype=self.input_to_dtype[key]).realize()
+
+    # Update numpy inputs
+    for key, value in numpy_inputs.items():
+      if key not in imgs_cl:
+        self.inputs[key] = Tensor(value, device=self.input_to_device[key], dtype=self.input_to_dtype[key]).realize()
+
+    return self.inputs
+
+  def run_model(self):
+    return self.model_run(**self.inputs).numpy().flatten()
+
+
+class ONNXRunner(ModelRunner):
+  """ONNX implementation of model runner for non-TICI hardware."""
+
+  def __init__(self):
+    super().__init__()
+    self.runner = make_onnx_cpu_runner(MODEL_PATH)
+
+    self.input_to_nptype = {
+      model_input.name: ORT_TYPES_TO_NP_TYPES[model_input.type]
+      for model_input in self.runner.get_inputs()
+    }
+
+  def prepare_inputs(self, imgs_cl: dict[str, CLMem], numpy_inputs: dict[str, np.ndarray], frames: dict[str, DrivingModelFrame]) -> dict:
+    self.inputs = numpy_inputs
+    for key in imgs_cl:
+      self.inputs[key] = frames[key].buffer_from_cl(imgs_cl[key]).reshape(self.input_shapes[key]).astype(dtype=self.input_to_nptype[key])
+    return self.inputs
+
+  def run_model(self):
+    return self.runner.run(None, self.inputs)[0].flatten()
diff --git a/sunnypilot/models/fetcher.py b/sunnypilot/models/fetcher.py
index 2a1fa1d8f..f543b00a7 100644
--- a/sunnypilot/models/fetcher.py
+++ b/sunnypilot/models/fetcher.py
@@ -72,13 +72,12 @@ class ModelParser:
     model_bundle.generation = int(value["generation"])
     model_bundle.environment = value["environment"]
     model_bundle.runner = value.get("runner", custom.ModelManagerSP.Runner.snpe)
+    model_bundle.is20hz = value.get("is_20hz", False)
 
     return model_bundle
 
   @staticmethod
   def parse_models(json_data: dict) -> list[custom.ModelManagerSP.ModelBundle]:
-    # TODO-SP: Remove the following filter once we add support for tinygrad model switcher
-    json_data = {k: v for k, v in json_data.items() if v.get("runner", -1) == custom.ModelManagerSP.Runner.snpe}
     return [ModelParser._parse_bundle(key, value) for key, value in json_data.items()]