---
license: apache-2.0
language:
- en
base_model:
- openai/gpt-oss-120b
library_name: mlx
pipeline_tag: text-generation
tags:
- vllm
- mlx
- apple-silicon
- gpt-oss
- quantized
- mxfp4
inference: false
widget:
- text: Summarize the operational risks in this deployment plan.
  example_title: Reasoning prompt
---

# gpt-oss-120b-mlx-mxfp4

`gpt-oss-120b-mlx-mxfp4` is an MLX MXFP4 checkpoint derived from `openai/gpt-oss-120b`, intended for local text generation on Apple Silicon.

## Intended use

- Local text generation and chat-style prompting on Apple Silicon
- MLX-LM experimentation with the declared upstream model family
- Offline or operator-controlled inference workflows

## Out of scope

- Safety-critical decisions without domain expert review
- Claims of benchmark superiority not backed by published evaluation data
- Non-MLX runtime guarantees; this card documents the shipped HF checkpoint, not every possible serving stack

## Training and conversion metadata

| Parameter | Value |
|---|---|
| Repository | `LibraxisAI/gpt-oss-120b-mlx-mxfp4` |
| Base model | `openai/gpt-oss-120b` |
| Task | `text-generation` |
| Library | `mlx` |
| Format | MLX / Apple Silicon checkpoint |
| Quantization | MXFP4 |
| Architecture | GptOssForCausalLM |
| Model files | 13 |
| Config model_type | `gpt_oss` |

This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.

## Tested inference path

> **Inference for this checkpoint has been tested with [`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server).**\
> This is the recommended tested path for operator-controlled local inference on Apple Silicon.

| Aspect | Status |
|---|---|
| Tested runtime | `LibraxisAI/mlx-batch-server` |
| Target hardware | Apple Silicon |
| Inference mode | Local / self-hosted |
| Hugging Face Hosted Inference | Disabled for this repository (`inference: false`) |

This does not claim compatibility with every possible serving stack. It documents the path that has been exercised for this published checkpoint.

## Usage

### CLI

```bash
pip install mlx-lm

mlx_lm.generate \
  --model LibraxisAI/gpt-oss-120b-mlx-mxfp4 \
  --prompt "Summarize the key signals in this document and list the next action items." \
  --max-tokens 400
```

### Python

```python
from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/gpt-oss-120b-mlx-mxfp4")

prompt = "Summarize the key signals in this document and list the next action items."
response = generate(model, tokenizer, prompt=prompt, max_tokens=400)
print(response)
```

### Multi-turn with the chat template

This checkpoint follows the tokenizer/chat-template contract inherited from `openai/gpt-oss-120b` when the
template is present in the repository:

```python
from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/gpt-oss-120b-mlx-mxfp4")

messages = [
    {"role": "user", "content": "Summarize the key signals in this document and list the next action items."},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=400)
print(response)
```

## Example output

No public sample output is currently declared for this checkpoint.

## Quantization notes

| Aspect | Original/base checkpoint | This checkpoint |
|---|---|---|
| Lineage | `openai/gpt-oss-120b` | `LibraxisAI/gpt-oss-120b-mlx-mxfp4` |
| Runtime target | Upstream runtime format | MLX on Apple Silicon |
| Quantization | Base precision or upstream-declared format | MXFP4 |
| Published quality delta | Not declared in public metadata | Not declared in public metadata |

## Limitations

- No public benchmarks for this checkpoint are declared in the model metadata.
- No public benchmark claims are made by this card unless listed in the frontmatter.
- Validate outputs on your own domain data before relying on this checkpoint.
- Memory use and speed depend heavily on the exact Apple Silicon generation, unified-memory size, and prompt length.

## License

`apache-2.0`. Check the upstream/base model license as well when a base model is declared.

## Citation

```bibtex
@misc{libraxisai-gpt-oss-120b-mlx-mxfp4,
  title = {gpt-oss-120b-mlx-mxfp4},
  author = {LibraxisAI},
  year = {2026},
  howpublished = {\url{https://huggingface.co/LibraxisAI/gpt-oss-120b-mlx-mxfp4}},
  note = {MLX checkpoint published by LibraxisAI}
}
```
---

𝚅𝚒𝚋𝚎𝚌𝚛𝚊𝚏𝚝𝚎𝚍. with AI Agents by VetCoders (c)2024-2026 LibraxisAI