MLX Community · First MLX build 2 Mar 2026
Qwen3.5-9B
MLX
TextVision apache-2.0
A 9.4B parameter vision and text model, with 16 MLX builds, from 4-bit to MXFP8.
- Parameters
- 9.4B From Hugging Face
- Quantisation
- 4-bit Qwen3.5-9B-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 6.0 GB Weights, estimated
- Downloads
- 25K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 16 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 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/Qwen3.5-9B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
16 on mlx-community| Qwen3.5-9B-4bit | 4-bit | 6.0 GB | 9 GB | 25K |
|---|---|---|---|---|
| Qwen3.5-9B-5bit | 5-bit | 7.1 GB | 10 GB | 274 |
| Qwen3.5-9B-6bit | 6-bit | 8.2 GB | 12 GB | 1.2K |
| Qwen3.5-9B-8bit | 8-bit | 10.4 GB | 14 GB | 3.0K |
| Qwen3.5-9B-bf16 | bf16 | 18.8 GB | 24 GB | 1.8K |
| Qwen3.5-9B-3bit | 3-bit | — | — | 0 |
| Qwen3.5-9B-mixed_2_6 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_3_4 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_3_5 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_3_6 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_3_8 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_4_6 | Unstated | — | — | 0 |
| Qwen3.5-9B-mixed_4_8 | Unstated | — | — | 0 |
| Qwen3.5-9B-mxfp4 | MXFP4 | — | — | 0 |
| Qwen3.5-9B-mxfp8 | MXFP8 | — | — | 0 |
| Qwen3.5-9B-nvfp4 | Unstated | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.