gpt-oss-20b-mlx-mxfp4

gpt-oss-20b-mlx-mxfp4 is an MLX MXFP4 checkpoint derived from openai/gpt-oss-20b, 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-20b-mlx-mxfp4
Base model	openai/gpt-oss-20b
Task	text-generation
Library	mlx
Format	MLX / Apple Silicon checkpoint
Quantization	MXFP4
Architecture	GptOssForCausalLM
Model files	3
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.

Usage

CLI

pip install mlx-lm

mlx_lm.generate \
  --model LibraxisAI/gpt-oss-20b-mlx-mxfp4 \
  --prompt "Summarize the key signals in this document and list the next action items." \
  --max-tokens 400

Python

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/gpt-oss-20b-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-20b when the template is present in the repository:

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/gpt-oss-20b-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. Run the usage example above against your own prompt or audio/image input to inspect behavior.

Quantization notes

Aspect	Original/base checkpoint	This checkpoint
Lineage	openai/gpt-oss-20b	LibraxisAI/gpt-oss-20b-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

@misc{libraxisai-gpt-oss-20b-mlx-mxfp4,
  title = {gpt-oss-20b-mlx-mxfp4},
  author = {LibraxisAI},
  year = {2026},
  howpublished = {\url{https://huggingface.co/LibraxisAI/gpt-oss-20b-mlx-mxfp4}},
  note = {MLX checkpoint published by LibraxisAI}
}

Inference tested on

LibraxisAI/mlx-batch-server

Related

• Base model: openai/gpt-oss-20b

---

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