MLX Community · First MLX build 24 Dec 2025
Qwen3-VL-8B-NSFW-Caption-V4.5
MLX
apache-2.0
A 8.8B parameter model, with one MLX build at MXFP4.
- Parameters
- 8.8B From Hugging Face
- Quantisation
- MXFP4 Qwen3-VL-8B-NSFW-Caption-V4.5-mxfp4
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.8 GB Weights, estimated
- Downloads
- 862 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 GB at MXFP4
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3-VL-8B-NSFW-Caption-V4.5-mxfp4MLX builds
1 on mlx-community| Qwen3-VL-8B-NSFW-Caption-V4.5-mxfp4 | MXFP4 | 5.8 GB | 9 GB | 862 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.