---
license: apache-2.0
base_model: Qwen/Qwen3-Coder-Next
pipeline_tag: text-generation
library_name: mlx
tags:
  - mlx
  - apple-silicon
  - qwen3-next
  - coding
  - mixture-of-experts
  - quantized
  - 6-bit
  - mirror
  - automatosx
  - ax-engine
---

# AX Qwen3 Coder Next MLX 6-bit

> **Parameter count:** approximately 79.67B logical parameters (80B total,
> 3B active per token). `6-bit` is the quantization precision, not a 6B
> model-size claim.

This is a revision-pinned, transparent mirror of
[mlx-community/Qwen3-Coder-Next-6bit](https://huggingface.co/mlx-community/Qwen3-Coder-Next-6bit)
at commit `9d12cc36cc6c386ffd04f7c8f0de6ccb29c5927e`.

The model weights, index, configuration, tokenizer, chat template, generation
configuration, and tool-parser files are byte-identical to that upstream
revision. AutomatosX did not fine-tune, merge, re-quantize, or otherwise alter
the model artifacts. We add only mirror documentation, a copy of the declared
Apache 2.0 license, and machine-readable provenance.

## Model details

- Base model: [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next)
- Format: MLX Safetensors for Apple Silicon
- Architecture: Qwen3NextForCausalLM, mixture of experts
- Main quantization: 6-bit affine, group size 64
- Quantization exceptions: router and shared-expert gate tensors remain 8-bit,
  as defined by the unchanged upstream config
- Layers: 48
- Experts: 512 total, 10 selected per token
- Configured context limit: 262,144 tokens
- Weight shards: 13, totaling 64,749,929,465 bytes
- Upstream conversion tool: mlx-lm 0.30.5

## Download

~~~bash
hf download AutomatosX/AX-Qwen3-Coder-Next-MLX-6bit \
  --local-dir ./AX-Qwen3-Coder-Next-MLX-6bit
~~~

## Use with MLX-LM

~~~bash
pip install mlx-lm
mlx_lm.generate \
  --model AutomatosX/AX-Qwen3-Coder-Next-MLX-6bit \
  --prompt "Write a Python function that merges two sorted lists."
~~~

Applications should apply the included chat template for conversational or
tool-using prompts.

## Serve with AX Engine

You can also serve the downloaded model through the OpenAI-compatible API in
[AX Engine](https://github.com/defai-digital/ax-engine):

~~~bash
ax-engine serve ./AX-Qwen3-Coder-Next-MLX-6bit --port 31418
~~~

## Mirror policy and provenance

This release is meant to group a required upstream artifact under the
AutomatosX catalog, not to claim a new conversion. `UPSTREAM_README.md`
preserves the original upstream model card. `ax_provenance.json` pins the
source commit and records SHA-256 values and sizes for every mirrored artifact.

This is a standard direct-decoding model. It does not contain an MTP head and
no MTP conversion was applied.

## License

The upstream model metadata declares Apache License 2.0. See `LICENSE`, the
upstream model card, and the base-model card for limitations and responsible-use
guidance.