unsloth/meta-Llama-3.1-8B-unsloth-bnb-4bit

Quantization vs meta-llama/Llama-3.1-8B-Instruct. unsloth/meta-Llama-3.1-8B-unsloth-bnb-4bit is a quantized version of the other (U8/BF16).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse