Llama-3.1-Nemotron-70B-Instruct-HF-4bit
mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-4bit
Text generation · transformers
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-Nemotron-70B-Instruct-HF-4bit --prompt "Hello"
Details
- Base model
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF (quantized) · Llama 3.1 Nemotron 70B Instruct HF on the radar →
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 163 in the last 30 days · 5.0K all time · 2 likes
- Published
- 2024-10-17 · updated 2024-10-17 (2y ago)
- Languages
- en
- Tags
- llama, nvidia, llama3.1
Other MLX builds of nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit | 4-bit | ≈ 39.7 GB | 48 GB+ | 1.2K |
| Llama-3.1-Nemotron-70B-Instruct-HF-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 163 |
| Llama-3.1-Nemotron-70B-Instruct-HF-8bit | 8-bit | ≈ 75.0 GB | 96 GB+ | 160 |
| Llama-3.1-Nemotron-70B-Instruct-HF-bf16 | bf16 | ≈ 141 GB | 192 GB+ | 250 |
| Llama-3.1-Nemotron-70B-Instruct-HF | — | ≈ 141 GB | 192 GB+ | 131 |