Trackdub Phi 4 Mini Gpu Int4
This repository repackages the gpu/gpu-int4-rtn-block-32 configuration from Microsoft's official ONNX release microsoft/Phi-4-mini-instruct-onnx. It is not a newly trained model. This is an unofficial community...
Model source
- Kind
- Other
- File size
- 280 KB
- Base model
- microsoft/Phi-4-mini-instruct-onnx
- Version
- vRevision 8023bb7
- Updated
- Oct 3, 2026
- Publisher
- @tonythethompson
- Downloads
- 0
- Tasks
- Text generation
- Source
- Hugging Face
Source description
Phi-4 Mini Instruct — GPU INT4 (ONNX Runtime GenAI)
This repository repackages the gpu/gpu-int4-rtn-block-32 configuration from Microsoft's
official ONNX release
microsoft/Phi-4-mini-instruct-onnx.
It is not a newly trained model. This is an unofficial community repackage; Microsoft is
the original author and license holder.
Source
| Field | Value |
|---|---|
| Upstream model | microsoft/Phi-4-mini-instruct-onnx |
| Upstream source revision | fc04c8f93df696602fd9f300a30d1bf2e3081347 |
| Export tool/script | Microsoft ONNX Runtime GenAI model builder (upstream Phi ONNX bundle) |
| Quantization recipe | ONNX Runtime GenAI RTN INT4 (gpu-int4-rtn-block-32) |
Files
All files are under gpu/gpu-int4-rtn-block-32/:
| File | Size | Description |
|---|---|---|
model.onnx | ~280 KB | INT4 ONNX graph |
model.onnx.data | ~3 GB | External weights |
genai_config.json | ~2 KB | ONNX Runtime GenAI session config |
config.json | ~2 KB | Model config |
configuration_phi3.py | ~11 KB | Phi-3/4 config class |
tokenizer.json + tokenizer_config.json | ~15 MB | Tokenizer |
vocab.json + merges.txt | ~6 MB | Vocabulary / merges |
added_tokens.json + special_tokens_map.json | <1 KB | Special tokens |
Intended Use
A 4-bit, GPU-targeted build of Phi-4-Mini-Instruct for local text generation and
translation. Targets NVIDIA CUDA and DirectML (Windows) execution paths where a capable
GPU is available. A CPU variant is in
tonythethompson/phi-4-mini-instruct-cpu-int4-onnx.
Runtime Notes
- Designed for ONNX Runtime GenAI compatible runtimes.
- GPU execution: CUDA (
onnxruntime-genai-cuda) or DirectML (onnxruntime-genai-directml). - Context length: 128K tokens (inherited from Phi-4-Mini-Instruct).
- Validate on the target execution provider before production use.
Precision and Packaging
Export tooling, precision, and quantization are recorded in the Source table above. This packaging mirror does not publish independent parity benchmarks; validate on your target execution provider before production use.
Limitations
- English-dominant training; quality on lower-resource languages may degrade.
- INT4 quantization introduces approximation error relative to the base FP16/FP32 model.
- No repository-specific translation quality evaluation is documented here.
- Validate on your target language pair before production use.
License
MIT — inherited from
microsoft/Phi-4-mini-instruct-onnx. This packaging repo adds no new license terms.
Sources
1 source
Sources
1 sourceVerified Oct 3
Model artifacts
1 artifact
Model artifacts
1 artifactgpu/gpu-int4-rtn-block-32/model.onnx
onnx · 280 KB · SHA-256 f8ff300b8571…5250 · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: mit base_model: microsoft/Phi-4-mini-instruct-onnx base_model_relation: quantized pipeline_tag: text-generation library_name: onnxruntime-genai language: - ar - zh - cs - da - nl - en - fi - fr - de - he - hu - it - ja - ko - "no" - pl - pt - ru - es - sv - th - tr - uk tags: - onnx - onnxruntime-genai - phi4 - phi4-mini - int4 - gpu - text-generation - translation --- # Phi-4 Mini Instruct — GPU INT4 (ONNX Runtime GenAI) This repository repackages the `gpu/gpu-int4-rtn-block-32` configuration from Microsoft's official ONNX release [microsoft/Phi-4-mini-instruct-onnx](https://huggingface.co/microsoft/Phi-4-mini-instruct-onnx). It is not a newly trained model. This is an unofficial community repackage; Microsoft is the original author and license holder. ## Source | Field | Value | |---|---| | Upstream model | [microsoft/Phi-4-mini-instruct-onnx](https://huggingface.co/microsoft/Phi-4-mini-instruct-onnx) | | Upstream source revision | `fc04c8f93df696602fd9f300a30d1bf2e3081347` | | Export tool/script | Microsoft ONNX Runtime GenAI model builder (upstream Phi ONNX bundle) | | Quantization recipe | ONNX Runtime GenAI RTN INT4 (`gpu-int4-rtn-block-32`) | ## Files All files are under `gpu/gpu-int4-rtn-block-32/`: | File | Size | Description | |---|---|---| | `model.onnx` | ~280 KB | INT4 ONNX graph | | `model.onnx.data` | ~3 GB | External weights | | `genai_config.json` | ~2 KB | ONNX Runtime GenAI session config | | `config.json` | ~2 KB | Model config | | `configuration_phi3.py` | ~11 KB | Phi-3/4 config class | | `tokenizer.json` + `tokenizer_config.json` | ~15 MB | Tokenizer | | `vocab.json` + `merges.txt` | ~6 MB | Vocabulary / merges | | `added_tokens.json` + `special_tokens_map.json` | <1 KB | Special tokens | ## Intended Use A 4-bit, GPU-targeted build of Phi-4-Mini-Instruct for local text generation and translation. Targets NVIDIA CUDA and DirectML (Windows) execution paths where a capable GPU is available. A CPU variant is in [`tonythethompson/phi-4-mini-instruct-cpu-int4-onnx`](https://huggingface.co/tonythethompson/phi-4-mini-instruct-cpu-int4-onnx). ## Runtime Notes - Designed for ONNX Runtime GenAI compatible runtimes. - GPU execution: CUDA (`onnxruntime-genai-cuda`) or DirectML (`onnxruntime-genai-directml`). - Context length: 128K tokens (inherited from Phi-4-M...
Source context: 0 downloads · 0 likes · Pipeline text-generation · Library onnxruntime-genai · Repo tonythethompson/Phi-4-Mini-Instruct-GPU-INT4-ONNX
Source context: 0 downloads · 0 likes · Pipeline text-generation · Library onnxruntime-genai · Repo tonythethompson/trackdub-phi-4-mini-gpu-int4
