MLX Community · First MLX build 6 Aug 2025
VisualQuality-R1-7B
MLX
Text mit
A 8.3B parameter reinforcement learning model, with 4 MLX builds, from bf16 to 6-bit.
- Parameters
- 8.3B From Hugging Face
- Quantisation
- 4-bit VisualQuality-R1-7B-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 59 This build, last 30 days
- Task
- Reinforcement learning Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/VisualQuality-R1-7B-4bitMLX builds
4 on mlx-community| VisualQuality-R1-7B-bf16 | bf16 | 16.6 GB | 21 GB | 13 |
|---|---|---|---|---|
| VisualQuality-R1-7B-4bit | 4-bit | — | — | 59 |
| VisualQuality-R1-7B-8bit | 8-bit | — | — | 53 |
| VisualQuality-R1-7B-6bit | 6-bit | — | — | 24 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.