Llama-3.1-405B-Instruct-8bit
mlx-community/Llama-3.1-405B-Instruct-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
406B
Weights (est.)
≈ 431 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-3.1-405B-Instruct-8bit --prompt "Hello"
Details
- Base model
- meta-llama/Llama-3.1-405B-Instruct (quantized)
- Vendor
- Meta · Llama
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- llama3.1
- Downloads
- 123 in the last 30 days · 1.3K all time · 2 likes
- Published
- 2024-11-06 · updated 2024-11-06 (2y ago)
- Languages
- en, de, fr, it, pt, hi, es, th
- Tags
- llama, facebook, meta, pytorch, llama-3
Other MLX builds of meta-llama/Llama-3.1-405B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Meta-Llama-3.1-405B-Instruct-8bit | 8-bit | ≈ 431 GB | 512 GB+ | 160 |
| Llama-3.1-405B-Instruct-8bit (this one) | 8-bit | ≈ 431 GB | 512 GB+ | 123 |