timmx 0.3.0

Extensible CLI and Python package for exporting timm models.

timmx

An extensible CLI and Python package for exporting timm models to various deployment formats. Born out of having too many one-off export scripts for fine-tuned timm models — timmx unifies them behind a single command-line interface with a plugin-based backend system.

Supported Formats

Format	Command	Output
ONNX	timmx export onnx	.onnx
Core ML	timmx export coreml	.mlpackage / .mlmodel
LiteRT / TFLite	timmx export litert	.tflite
ncnn	timmx export ncnn	directory (.param + .bin)
TensorRT	timmx export tensorrt	.engine
ExecuTorch	timmx export executorch	.pte
torch.export	timmx export torch-export	.pt2
TorchScript	timmx export torchscript	.pt

Requirements

• Python >=3.11
• uv

Installation

Core install (includes timm, torch, typer, rich):

pip install timmx

Install with specific backend extras:

pip install 'timmx[onnx]'           # ONNX export
pip install 'timmx[coreml]'         # Core ML export
pip install 'timmx[litert]'         # LiteRT/TFLite export
pip install 'timmx[ncnn]'           # ncnn export (via pnnx)
pip install 'timmx[executorch]'     # ExecuTorch export (XNNPack, CoreML delegates)
pip install 'timmx[onnx,coreml]'    # multiple backends

TensorRT requires CUDA and must be installed separately:

pip install tensorrt  # Linux/Windows with CUDA only

Note: The executorch and litert extras have conflicting torch version requirements (executorch needs torch>=2.10.0, litert needs torch<2.10.0) and cannot be installed in the same environment.

Check which backends are available:

timmx doctor

Quick Start

uv sync --extra onnx --extra coreml --extra ncnn --group dev
uv run timmx doctor
uv run timmx --help

Usage Examples

ONNX

uv run timmx export onnx resnet18 --pretrained --output ./artifacts/resnet18.onnx

Export a fine-tuned checkpoint with dynamic batching:

uv run timmx export onnx resnet18 \
  --checkpoint ./checkpoints/model.pth \
  --input-size 3 224 224 \
  --dynamic-batch \
  --output ./artifacts/resnet18_finetuned.onnx

Exported models are automatically optimized with onnxslim (constant folding, dead-code elimination, operator fusion). To skip optimization:

uv run timmx export onnx resnet18 --pretrained --no-slim --output ./artifacts/resnet18.onnx

Core ML

uv run timmx export coreml resnet18 \
  --pretrained \
  --convert-to mlprogram \
  --compute-precision float16 \
  --output ./artifacts/resnet18.mlpackage

Using torch.export as source (beta):

uv run timmx export coreml resnet18 \
  --pretrained \
  --source torch-export \
  --convert-to mlprogram \
  --compute-precision float16 \
  --output ./artifacts/resnet18_te.mlpackage

Flexible batch size:

uv run timmx export coreml resnet18 \
  --dynamic-batch \
  --batch-size 2 \
  --batch-upper-bound 8 \
  --output ./artifacts/resnet18_dynamic.mlpackage

LiteRT / TFLite

Supported modes: fp32, fp16, dynamic-int8, int8.

uv run timmx export litert resnet18 \
  --mode fp16 \
  --output ./artifacts/resnet18_fp16.tflite

INT8 with calibration data (point to an image directory — timm transforms are applied automatically):

uv run timmx export litert resnet18 \
  --mode int8 \
  --calibration-data ./my-images/ \
  --output ./artifacts/resnet18_int8.tflite

Limit the number of calibration images loaded:

uv run timmx export litert resnet18 \
  --mode int8 \
  --calibration-data ./my-images/ \
  --calibration-samples 64 \
  --output ./artifacts/resnet18_int8.tflite

A pre-saved torch tensor (N, C, H, W) is also accepted:

uv run timmx export litert resnet18 \
  --mode int8 \
  --calibration-data ./calibration.pt \
  --calibration-steps 8 \
  --output ./artifacts/resnet18_int8.tflite

Use --random-calibration to skip providing real data (not recommended for production):

uv run timmx export litert resnet18 \
  --mode int8 \
  --random-calibration \
  --output ./artifacts/resnet18_int8.tflite

NHWC input layout:

uv run timmx export litert resnet18 \
  --mode fp32 \
  --nhwc-input \
  --output ./artifacts/resnet18_nhwc.tflite

ncnn

Exports via pnnx and writes a deployment-ready ncnn model directory containing model.ncnn.param, model.ncnn.bin, and model_ncnn.py. pnnx intermediate files are removed automatically.

uv run timmx export ncnn resnet18 \
  --pretrained \
  --output ./artifacts/resnet18_ncnn

Export without fp16 weight quantization:

uv run timmx export ncnn resnet18 \
  --pretrained \
  --no-fp16 \
  --output ./artifacts/resnet18_ncnn_fp32

TensorRT

Requires an NVIDIA GPU with CUDA and the tensorrt package (pip install tensorrt).

uv run timmx export tensorrt resnet18 \
  --pretrained \
  --mode fp16 \
  --output ./artifacts/resnet18_fp16.engine

INT8 with calibration (image directory or torch tensor):

uv run timmx export tensorrt resnet18 \
  --pretrained \
  --mode int8 \
  --calibration-data ./my-images/ \
  --output ./artifacts/resnet18_int8.engine

Dynamic batch size:

uv run timmx export tensorrt resnet18 \
  --pretrained \
  --dynamic-batch \
  --batch-size 4 \
  --batch-min 1 \
  --batch-max 32 \
  --output ./artifacts/resnet18_dynamic.engine

ExecuTorch

Export with XNNPack delegation (default, runs on CPU across all platforms):

uv run timmx export executorch resnet18 \
  --pretrained \
  --output ./artifacts/resnet18.pte

CoreML delegation (macOS — targets Apple Neural Engine / GPU / CPU):

uv run timmx export executorch resnet18 \
  --pretrained \
  --delegate coreml \
  --output ./artifacts/resnet18_coreml.pte

CoreML with explicit fp32 compute precision (default is fp16):

uv run timmx export executorch resnet18 \
  --pretrained \
  --delegate coreml \
  --compute-precision float32 \
  --output ./artifacts/resnet18_coreml_fp32.pte

INT8 quantized with XNNPack:

uv run timmx export executorch resnet18 \
  --pretrained \
  --mode int8 \
  --calibration-data ./my-images/ \
  --output ./artifacts/resnet18_int8.pte

INT8 quantized with CoreML:

uv run timmx export executorch resnet18 \
  --pretrained \
  --delegate coreml \
  --mode int8 \
  --output ./artifacts/resnet18_coreml_int8.pte

Dynamic batch size:

uv run timmx export executorch resnet18 \
  --pretrained \
  --dynamic-batch \
  --batch-size 2 \
  --output ./artifacts/resnet18_dynamic.pte

torch.export

uv run timmx export torch-export resnet18 \
  --pretrained \
  --dynamic-batch \
  --batch-size 2 \
  --output ./artifacts/resnet18.pt2

When using --dynamic-batch, set --batch-size to at least 2 so PyTorch can capture a symbolic batch dimension.

TorchScript

uv run timmx export torchscript resnet18 \
  --pretrained \
  --output ./artifacts/resnet18.pt

Use torch.jit.script instead of the default trace:

uv run timmx export torchscript resnet18 \
  --pretrained \
  --method script \
  --output ./artifacts/resnet18_scripted.pt

Diagnostics

Run timmx doctor to check your installation and see which backends are available:

timmx doctor

This shows the timmx version, Python/torch versions, and a table of backend availability with install hints for any missing dependencies.

Roadmap

• ONNX
• Core ML
• LiteRT / TFLite
• ncnn
• torch.export
• TensorRT
• TorchScript
• ExecuTorch (XNNPack + CoreML delegates)
• OpenVINO
• TensorFlow (SavedModel / .pb)
• TensorFlow.js
• TFLite Edge TPU
• RKNN
• MNN
• PaddlePaddle

Development

uv sync --extra onnx --extra coreml --extra ncnn --group dev  # install extras + pytest
uvx ruff format .                                              # format
uvx ruff check .                                               # lint
uv run pytest                                                  # test
uv build                                                       # build

Adding a New Backend

See CONTRIBUTING.md for a step-by-step guide on implementing and registering a new export backend.

AI Disclaimer

This project is developed with the assistance of AI tools. The original export logic comes from various standalone scripts I wrote for exporting fine-tuned timm models to different deployment formats. The process of consolidating these scripts into a unified CLI tool has been aided by AI, with my oversight at every step, reviewing generated code, manually fixing issues during backend porting, and validating that exports produce correct results.