unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
Quantization vs meta-llama/Llama-3.2-1B-Instruct. unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit is a quantized version of the other (BF16/U8).
2 derivatives checked
- HanJeongSeop/GRPO_Llama3_1B: Quantization
- Ryder99/Llama-3.2-1B-Instruct-Hindi: Quantization
2 other repos hold byte-for-byte identical weight files.