MLX Community · First MLX build 16 Apr 2025
VL-Rethinker-72B
MLX
Text apache-2.0
A visual question answering model, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit VL-Rethinker-72B-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 27 This build, last 30 days
- Task
- Visual question answering 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/VL-Rethinker-72B-4bitMLX builds
4 on mlx-community| VL-Rethinker-72B-4bit | 4-bit | — | — | 27 |
|---|---|---|---|---|
| VL-Rethinker-72B-6bit | 6-bit | — | — | 19 |
| VL-Rethinker-72B-fp16 | fp16 | — | — | 19 |
| VL-Rethinker-72B-8bit | 8-bit | — | — | 17 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.