MLX Community · First MLX build 28 Mar 2026
Qwen3.5-27B-heretic-v3
MLX
TextVision apache-2.0
A 27B parameter vision and text model, with one MLX build at MXFP8.
- Parameters
- 27B From Hugging Face
- Quantisation
- MXFP8 Qwen3.5-27B-heretic-v3-mxfp8
- Memory needed
- 35 GB Estimate, unified memory
- Download
- 29.5 GB Weights, estimated
- Downloads
- 38 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 35 GB at MXFP8
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/Qwen3.5-27B-heretic-v3-mxfp8 --image photo.jpg --prompt "Describe this image"MLX builds
1 on mlx-community| Qwen3.5-27B-heretic-v3-mxfp8 | MXFP8 | 29.5 GB | 35 GB | 38 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.