MLX Community · First MLX build 16 Feb 2026
Qwen3.5-397B-A17B
MLX
TextVision apache-2.0
A 397B parameter vision and text model, with 3 MLX builds, from 4-bit to 6-bit.
- Parameters
- 397B From Hugging Face
- Quantisation
- 4-bit Qwen3.5-397B-A17B-4bit
- Memory needed
- 253 GB Estimate, unified memory
- Download
- 224 GB Weights, estimated
- Downloads
- 857 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 253 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/Qwen3.5-397B-A17B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| Qwen3.5-397B-A17B-4bit | 4-bit | 224 GB | 253 GB | 857 |
|---|---|---|---|---|
| Qwen3.5-397B-A17B-5bit | 5-bit | 273 GB | 308 GB | 56 |
| Qwen3.5-397B-A17B-6bit | 6-bit | 323 GB | 363 GB | 177 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.