Meta · First MLX build 6 Apr 2025
Llama-4-Scout-17B-16E
MLX
Text llama4
A 108B parameter text generation model from Meta, with 9 MLX builds, from 4-bit to bf16.
- Parameters
- 108B From Hugging Face
- Quantisation
- 4-bit Llama-4-Scout-17B-16E-Instruct-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 1.9K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 9 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-Instruct-4bit --image photo.jpg --prompt "Describe this image"MLX builds
9 on mlx-community| meta-llama-Llama-4-Scout-17B-16E-4bit | 4-bit | 60.6 GB | 70 GB | 583 |
|---|---|---|---|---|
| meta-llama-Llama-4-Scout-17B-16E-6bit | 6-bit | 87.6 GB | 100 GB | 59 |
| meta-llama-Llama-4-Scout-17B-16E-8bit | 8-bit | 115 GB | 130 GB | 237 |
| meta-llama-Llama-4-Scout-17B-16E-fp16 | fp16 | 216 GB | 243 GB | 62 |
| meta-llama-Llama-4-Scout-17B-16E-bf16 | bf16 | 216 GB | 243 GB | 57 |
| Llama-4-Scout-17B-16E-Instruct-4bit | 4-bit | — | — | 1.9K |
| Llama-4-Scout-17B-16E-Instruct-6bit | 6-bit | — | — | 186 |
| Llama-4-Scout-17B-16E-Instruct-8bit | 8-bit | — | — | 178 |
| meta-llama-Llama-4-Scout-17B-16E-Instruct-bf16 | bf16 | — | — | 97 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.