meta-llama-Llama-4-Scout-17B-16E-8bit
mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
108B
Weights (est.)
≈ 115 GB
Mac memory (est.)
192 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-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit --prompt "Hello"
Details
- Base model
- meta-llama/Llama-4-Scout-17B-16E (quantized)
- Vendor
- Meta · Llama
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- llama4
- Downloads
- 241 in the last 30 days · 45K all time · 4 likes
- Published
- 2025-04-06 · updated 2025-04-06 (1y ago)
- Languages
- ar, de, en, es, fr, hi, id, it, pt, th, tl, vi
- Tags
- llama4, facebook, meta, pytorch, llama, llama-4
Other MLX builds of meta-llama/Llama-4-Scout-17B-16E
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| meta-llama-Llama-4-Scout-17B-16E-4bit | 4-bit | ≈ 60.6 GB | 96 GB+ | 573 |
| meta-llama-Llama-4-Scout-17B-16E-6bit | 6-bit | ≈ 87.6 GB | 128 GB+ | 62 |
| meta-llama-Llama-4-Scout-17B-16E-8bit (this one) | 8-bit | ≈ 115 GB | 192 GB+ | 241 |
| meta-llama-Llama-4-Scout-17B-16E-fp16 | fp16 | ≈ 216 GB | 256 GB+ | 67 |
| meta-llama-Llama-4-Scout-17B-16E-bf16 | bf16 | ≈ 216 GB | 256 GB+ | 64 |
| Llama-4-Scout-17B-16E-Instruct-4bit | 4-bit | — | — | 1.9K |
| Llama-4-Scout-17B-16E-Instruct-6bit | 6-bit | — | — | 185 |
| Llama-4-Scout-17B-16E-Instruct-8bit | 8-bit | — | — | 178 |
| meta-llama-Llama-4-Scout-17B-16E-Instruct-bf16 | bf16 | — | — | 99 |