orcarouter · First MLX build 15 Sept 2026
Qwen3.8-Flash-Next-Uncensored
MLX
TextVision qwen-community-1.0 Trending
A 180B parameter vision and text model from orcarouter, with 2 MLX builds, from 5-bit to 6-bit.
- Parameters
- 180B From Hugging Face
- Quantisation
- 5-bit Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp
- Memory needed
- 142 GB Estimate, unified memory
- Download
- 124 GB Weights, estimated
- Downloads
- 8.5K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 142 GB at 5-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-Uncensored-oQ5e-mtp --image photo.jpg --prompt "Describe this image"MLX builds
2 on mlx-community| Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp | 5-bit | 124 GB | 142 GB | 8.5K |
|---|---|---|---|---|
| Qwen3.8-Flash-Next-Uncensored-oQ6e-mtp | 6-bit | 147 GB | 167 GB | 2.1K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.