![](https://cdn-avatars.huggingface.co/v1/production/uploads/62ecdc18b72a69615d6bd857/E4lkPz1TZNLzIFr_dR273.png)
unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
Text Generation
•
Updated
•
90.1k
•
16
Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit
Note DeepSeek-R1 Distill Models:
Note Text-based LLMs:
Note Vision Models: