Llama-4-Maverick-17B-16E-Instruct-6bit
mlx-community/Llama-4-Maverick-17B-16E-Instruct-6bit
Text generation · mlx
6-bit Open on Hugging Face
Parameters
401B
Weights (est.)
≈ 326 GB
Mac memory (est.)
512 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/Llama-4-Maverick-17B-16E-Instruct-6bit --prompt "Hello"
Details
- Base model
- meta-llama/Llama-4-Maverick-17B-128E-Instruct (quantized)
- Vendor
- Meta · Llama
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- llama4
- Downloads
- 64 in the last 30 days · 8.3K all time · 2 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-Maverick-17B-128E-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-4-Maverick-17B-16E-Instruct-4bit | 4-bit | ≈ 225 GB | 256 GB+ | 172 |
| Llama-4-Maverick-17B-16E-Instruct-6bit (this one) | 6-bit | ≈ 326 GB | 512 GB+ | 64 |