Alibaba Qwen · First MLX build 22 Apr 2026 · In Core AI since 16 Oct 2026
Qwen3.6-27B
MLXCore AI
TextVision apache-2.0
A 28B parameter vision and text model from Alibaba Qwen, with 13 MLX builds, from 4-bit to MXFP8 and Apple Core AI export recipes for macOS.
- Parameters
- 28B From Hugging Face
- Quantisation
- 4-bit Qwen3.6-27B-4bit
- Memory needed
- 20 GB Estimate, unified memory
- Download
- 16.1 GB Weights, estimated
- Downloads
- 46K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 13 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 28B From Hugging Face
- Compression
- None Apple’s preset
- Memory needed
- — Parameter count not published
- Context
- 256K tokens Fixed at export
- Precision
- BF16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 16 Oct 2026 First registry commit
Memory
Will it fit?Needs about 20 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Qwen3.6-27B-4bit --image photo.jpg --prompt "Describe this image"Memory
There is no memory estimate: the parameter count for this model is not published on Hugging Face.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export qwen3.6-27b
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
13 on mlx-community| Qwen3.6-27B-MTP-4bit | 4-bit | 239 MB | 3 GB | 203 |
|---|---|---|---|---|
| Qwen3.6-27B-MTP-5bit | 5-bit | 292 MB | 3 GB | 45 |
| Qwen3.6-27B-MTP-bf16 | bf16 | 849 MB | 3 GB | 57 |
| Huihui-Qwen3.6-27B-abliterated-4.5bit-msq | 5-bit | 4.6 GB | 8 GB | 43 |
| Qwen3.6-27B-4bit | 4-bit | 16.1 GB | 20 GB | 46K |
| Qwen3.6-27B-OptiQ-4bit | 4-bit | 16.1 GB | 20 GB | 2.2K |
| Qwen3.6-27B-nvfp4 | 4-bit | 16.1 GB | 20 GB | 1.6K |
| Qwen3.6-27B-mxfp4 | MXFP4 | 16.1 GB | 20 GB | 97 |
| Qwen3.6-27B-5bit | 5-bit | 19.4 GB | 24 GB | 100 |
| Qwen3.6-27B-6bit | 6-bit | 22.8 GB | 28 GB | 203 |
| Qwen3.6-27B-8bit | 8-bit | 29.5 GB | 35 GB | 2.7K |
| Qwen3.6-27B-mxfp8 | MXFP8 | 29.5 GB | 35 GB | 783 |
| Qwen3.6-27B-bf16 | bf16 | 54.7 GB | 64 GB | 1.1K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| qwen3.6-27b | macOS | None | BF16 | 256K |