MLX Community · First MLX build 2 Nov 2026
Qwopus3.8-27B-Coder-Flash
MLX
TextVision apache-2.0 New
A 27B parameter vision and text model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 27B From Hugging Face
- Quantisation
- 8-bit Qwopus3.8-27B-Coder-Flash-8bit
- Memory needed
- 35 GB Estimate, unified memory
- Download
- 29.5 GB Weights, estimated
- Downloads
- 953 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 35 GB at 8-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/Qwopus3.8-27B-Coder-Flash-8bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| Qwopus3.8-27B-Coder-Flash-4bit | 4-bit | 16.1 GB | 20 GB | 874 |
|---|---|---|---|---|
| Qwopus3.8-27B-Coder-Flash-6bit | 6-bit | 22.8 GB | 28 GB | 679 |
| Qwopus3.8-27B-Coder-Flash-8bit | 8-bit | 29.5 GB | 35 GB | 953 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.