Jackrong · First MLX build 7 Aug 2026
DeepSeek-V4-Pro-Qwen3.5-9B
MLX
TextVision apache-2.0 Trending
A 9.4B parameter vision and text model from Jackrong, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 9.4B From Hugging Face
- Quantisation
- 4-bit DeepSeek-V4-Pro-Qwen3.5-9B-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 6.0 GB Weights, estimated
- Downloads
- 1.7K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 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/DeepSeek-V4-Pro-Qwen3.5-9B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| DeepSeek-V4-Pro-Qwen3.5-9B-4bit | 4-bit | 6.0 GB | 9 GB | 1.7K |
|---|---|---|---|---|
| DeepSeek-V4-Pro-Qwen3.5-9B-6bit | 6-bit | 8.2 GB | 12 GB | 361 |
| DeepSeek-V4-Pro-Qwen3.5-9B-8bit | 8-bit | 10.4 GB | 14 GB | 692 |
| DeepSeek-V4-Pro-Qwen3.5-9B-bf16 | bf16 | 18.8 GB | 24 GB | 435 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.