MLX Community · First MLX build 6 Apr 2025
Llama-4-Scout-17B-16E
MLX
TextVision llama4
A vision and text model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit Llama-4-Scout-17B-16E-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 117 This build, last 30 days
- Task
- Vision and text Text, Vision
- 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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Llama-4-Scout-17B-16E-4bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| Llama-4-Scout-17B-16E-4bit | 4-bit | — | — | 117 |
|---|---|---|---|---|
| Llama-4-Scout-17B-16E-6bit | 6-bit | — | — | 68 |
| Llama-4-Scout-17B-16E-8bit | 8-bit | — | — | 65 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.