Llama-3.2-11B-Vision-Instruct-8bit
mlx-community/Llama-3.2-11B-Vision-Instruct-8bit
Vision + text · transformers
8-bit Open on Hugging Face
Parameters
11B
Weights (est.)
≈ 11.3 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Llama-3.2-11B-Vision-Instruct-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- meta-llama/Llama-3.2-11B-Vision-Instruct (finetune)
- Vendor
- Meta · Llama
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- llama3.2
- Downloads
- 2.8K in the last 30 days · 31K all time · 9 likes
- Published
- 2024-10-18 · updated 2024-10-18 (2y ago)
- Languages
- en
- Tags
- mllama, llama-3, llama, meta, facebook, unsloth, deploy:azure
Other MLX builds of meta-llama/Llama-3.2-11B-Vision-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3.2-11B-Vision-Instruct-4bit | 4-bit | ≈ 6.0 GB | 16 GB+ | 2.6K |
| Llama-3.2-11B-Vision-Instruct-abliterated-4-bit | 4-bit | ≈ 6.0 GB | 16 GB+ | 447 |
| Llama-3.2-11B-Vision-Instruct-8bit (this one) | 8-bit | ≈ 11.3 GB | 16 GB+ | 2.8K |
| Llama-3.2-11B-Vision-Instruct-abliterated-8-bit | 8-bit | ≈ 11.3 GB | 16 GB+ | 317 |
| Llama-3.2-11B-Vision-Instruct-abliterated | — | ≈ 21.3 GB | 32 GB+ | 2.7K |