PrunaAI/Einstein-v6.1-Llama3-8B-bnb-4bit-smashed

Quantization vs Weyaxi/Einstein-v6.1-Llama3-8B. PrunaAI/Einstein-v6.1-Llama3-8B-bnb-4bit-smashed is a quantized version of the other (U8/F16).

On the Hub · Downloads on Model Pulse