---
license: apache-2.0
base_model: Qwen/Qwen3.6-27B
library_name: mlx
pipeline_tag: image-text-to-text
tags:
- mlx
- apple-silicon
- qwen3.6
- 2bit
---

# Qwen3.6-27B-MLX-2bit

## Summary

MLX 2bit (affine, 2-bit, group size 64) quantization of [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) at upstream revision `6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`, produced directly from the BF16 safetensors with `pipelines.mlx_direct_quantize` (majek repo). ~8.8 GiB on disk.

> **Runtime caveat:** this is a weights + config pack published ahead of runtime availability; the `qwen3_5` vision-language architecture is now supported upstream (mlx-lm PR #1345, merged 2026-06-04; mlx-vlm support available). No local inference smoke was performed on these artifacts, so the quality of this variant is not verified.

## Why this variant

Affine 2-bit, group size 64 — the smallest tier. Highest quality risk of the family (unverified; see the runtime caveat).

## Reproduce

```bash
python -m pipelines.mlx_direct_quantize --model qwen3.6-27b --base-dir /tmp/mlx-direct-release/qwen3.6-27b/base --out-dir /tmp/mlx-direct-release/qwen3.6-27b/2bit --bits 2 --mode affine --group-size 64
```

## Vision tower

The `model.visual.*` tower (333 tensors) is passed through unquantized in BF16 — only the text tower (`model.language_model.*`, `lm_head.*`) is quantized.

## Family

All MLX variants of this model ship together:

- `majentik/Qwen3.6-27B-MLX-2bit` (this repo)
- [majentik/Qwen3.6-27B-MLX-3bit](https://huggingface.co/majentik/Qwen3.6-27B-MLX-3bit)
- [majentik/Qwen3.6-27B-MLX-4bit](https://huggingface.co/majentik/Qwen3.6-27B-MLX-4bit)
- [majentik/Qwen3.6-27B-MLX-5bit](https://huggingface.co/majentik/Qwen3.6-27B-MLX-5bit)
- [majentik/Qwen3.6-27B-MLX-6bit](https://huggingface.co/majentik/Qwen3.6-27B-MLX-6bit)
- [majentik/Qwen3.6-27B-MLX-8bit](https://huggingface.co/majentik/Qwen3.6-27B-MLX-8bit)
- [majentik/Qwen3.6-27B-MLX-MXFP4](https://huggingface.co/majentik/Qwen3.6-27B-MLX-MXFP4)
- [majentik/Qwen3.6-27B-MLX-NVFP4](https://huggingface.co/majentik/Qwen3.6-27B-MLX-NVFP4)

## Provenance

- Upstream: [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) @ `6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`
- Quantization: bits=2, mode=affine, group_size=64 (text tower only)
- Toolchain: mlx 0.31.2, huggingface_hub 0.36.2
- Full details in [PROVENANCE.md](PROVENANCE.md) in this repo.

## License + attribution

Quantized by [majentik](https://huggingface.co/majentik) from [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B). All rights in the original model remain with its authors.

The upstream model is released under the Apache License 2.0 — see the upstream [LICENSE](https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE) file.