Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4 / README.md

card: full rewrite from canonical template

7391556 verified 4 days ago

4.59 kB

license: apache-2.0
language:
  - en
base_model:
  - Qwen/Qwen3-Next-80B-A3B-Instruct
library_name: mlx-lm
pipeline_tag: text-generation
tags:
  - mlx
  - text-generation
  - qwen
  - mxfp4
  - libraxisai
  - MoE
  - apple-silicon
  - quantized
inference: false
widget:
  - text: Summarize the operational risks in this deployment plan.
    example_title: Reasoning prompt

Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4

Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4 is an MLX MXFP4 checkpoint derived from Qwen/Qwen3-Next-80B-A3B-Instruct, 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/Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4`
Base model	`Qwen/Qwen3-Next-80B-A3B-Instruct`
Task	`text-generation`
Library	`mlx-lm`
Format	MLX / Apple Silicon checkpoint
Quantization	MXFP4
Architecture	Qwen3NextForCausalLM
Model files	9
Config model_type	`qwen3_next`

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/Qwen3-Next-80B-A3B-Instruct-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/Qwen3-Next-80B-A3B-Instruct-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 Qwen/Qwen3-Next-80B-A3B-Instruct when the template is present in the repository:

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/Qwen3-Next-80B-A3B-Instruct-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	`Qwen/Qwen3-Next-80B-A3B-Instruct`	`LibraxisAI/Qwen3-Next-80B-A3B-Instruct-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-qwen3-next-80b-a3b-instruct-mlx-mxfp4,
  title = {Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4},
  author = {LibraxisAI},
  year = {2026},
  howpublished = {\url{https://huggingface.co/LibraxisAI/Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4}},
  note = {MLX checkpoint published by LibraxisAI}
}

Inference tested on

LibraxisAI/mlx-batch-server

Base model: Qwen/Qwen3-Next-80B-A3B-Instruct

LibraxisAI
/

Qwen3-Next-80B-A3B-Instruct-MLX-MXFP4