unsloth/Llama-3.2-3B-unsloth-bnb-4bit

Quantization vs meta-llama/Llama-3.2-3B-Instruct. unsloth/Llama-3.2-3B-unsloth-bnb-4bit is a quantized version of the other (U8/BF16).

2 derivatives checked

• FritzStack/Llama3B-GoEmotions_4bit: Quantization
• Aasher/TibbScholar: Quantization

On the Hub · Downloads on Model Pulse