MLX Community · First MLX build 4 Jun 2025
Llama-3.2-11B-Vision-Surgical-CholecT50
MLX
nvidia-community-model-license
A 11B parameter model, with 3 MLX builds, from bf16 to 8-bit.
- Parameters
- 11B From Hugging Face
- Quantisation
- 4-bit Llama-3.2-11B-Vision-Surgical-CholecT50-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 73 This build, last 30 days
- Task
- —
- MLX builds
- 3 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/Llama-3.2-11B-Vision-Surgical-CholecT50-4bitMLX builds
3 on mlx-community| Llama-3.2-11B-Vision-Surgical-CholecT50-bf16 | bf16 | 21.3 GB | 26 GB | 65 |
|---|---|---|---|---|
| Llama-3.2-11B-Vision-Surgical-CholecT50-4bit | 4-bit | — | — | 73 |
| Llama-3.2-11B-Vision-Surgical-CholecT50-8bit | 8-bit | — | — | 54 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.