Alibaba Qwen · First MLX build 31 Aug 2026
Qwen3.8-Flash-Next
MLX
TextVision qwen-community-1.0 Trending
A 180B parameter vision and text model from Alibaba Qwen, with 5 MLX builds, from 2-bit to 8-bit.
- Parameters
- 180B From Hugging Face
- Quantisation
- 4-bit Qwen3.8-Flash-Next-4bit
- Memory needed
- 115 GB Estimate, unified memory
- Download
- 100 GB Weights, estimated
- Downloads
- 7.9K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 115 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/Qwen3.8-Flash-Next-4bit --image photo.jpg --prompt "Describe this image"MLX builds
5 on mlx-community| Qwen3.8-Flash-Next-OptiQ-2bit | 2-bit | 56.3 GB | 65 GB | 2.5K |
|---|---|---|---|---|
| Qwen3.8-Flash-Next-4bit | 4-bit | 100 GB | 115 GB | 7.9K |
| Qwen3.8-Flash-Next-4bit-mtp | 4-bit | 102 GB | 116 GB | 2.3K |
| Qwen3.8-Flash-Next-oQ6e-mtp | 6-bit | 147 GB | 167 GB | 956 |
| Qwen3.8-Flash-Next-oQ8e-mtp | 8-bit | 192 GB | 217 GB | 1.1K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.