Alibaba Qwen · First MLX build 14 Apr 2026 · In Core AI since 16 Oct 2026
Qwen3.5-122B-A10B
MLXCore AI
TextVision apache-2.0 Trending
A 125B parameter vision and text model from Alibaba Qwen, with 5 MLX builds, from 2-bit to MXFP8 and Apple Core AI export recipes for macOS.
- Parameters
- 125B From Hugging Face
- Quantisation
- MXFP8 Qwen3.5-122B-A10B-mxfp8
- Memory needed
- 149 GB Estimate, unified memory
- Download
- 131 GB Weights, estimated
- Downloads
- 829 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 125B 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 149 GB at MXFP8
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/Qwen3.5-122B-A10B-mxfp8 --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 qwen3.5-122b-a10b
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
5 on mlx-community| Qwen3.5-122B-A10B-OptiQ-2bit | 2-bit | 39.1 GB | 46 GB | 358 |
|---|---|---|---|---|
| Qwen3.5-122B-A10B-heretic-v2-2.34bit-msq | 34-bit | 43.3 GB | 51 GB | 81 |
| Qwen3.5-122B-A10B-mxfp4 | MXFP4 | 69.6 GB | 80 GB | 133 |
| Qwen3.5-122B-A10B-6bit-gs32 | 6-bit | 100 GB | 114 GB | 87 |
| Qwen3.5-122B-A10B-mxfp8 | MXFP8 | 131 GB | 149 GB | 829 |
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 |
|---|---|---|---|---|
| qwen3.5-122b-a10b | macOS | None | BF16 | 256K |