4-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 39.7 GB
Mac memory (est.)
48 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-Tulu-3-70B-4bit --prompt "Hello"
Details
- Base model
- allenai/Llama-3.1-Tulu-3-70B (quantized)
- Vendor
- Ai2 · OLMo
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 71 in the last 30 days · 316 all time · 0 likes
- Published
- 2024-11-25 · updated 2024-11-25 (1y ago)
- Languages
- en
- Tags
- llama
Other MLX builds of allenai/Llama-3.1-Tulu-3-70B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3.1-Tulu-3-70B-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 71 |
| Llama-3.1-Tulu-3-70B-6bit | 6-bit | ≈ 57.3 GB | 96 GB+ | 50 |