ffgn/Qwen2-0.5B-Inst-bnb-4bit_WikiMediaPT_AlpacaGPT4PT-GGFU

Quantization vs unsloth/Qwen2-0.5B-Instruct-bnb-4bit. unsloth/Qwen2-0.5B-Instruct-bnb-4bit is a quantized version of the other (BF16/U8).

On the Hub · Downloads on Model Pulse