r1-1776-distill-llama-70b-4bit
mlx-community/r1-1776-distill-llama-70b-4bit
Uncategorised · mlx
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.
Details
- Base model
- perplexity-ai/r1-1776-distill-llama-70b (quantized)
- Vendor
- perplexity-ai
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 24 in the last 30 days · 985 all time · 3 likes
- Published
- 2025-02-21 · updated 2025-02-21 (1y ago)
- Tags
- llama
Other MLX builds of perplexity-ai/r1-1776-distill-llama-70b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| r1-1776-distill-llama-70b-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 24 |
| r1-1776-distill-llama-70b-8bit | 8-bit | ≈ 75.0 GB | 96 GB+ | 38 |