dat-lequoc/vLLM-fast-apply-16bit-v0.13-Llama3.2-1B

Quantization vs unsloth/Llama-3.2-1B-Instruct-bnb-4bit. unsloth/Llama-3.2-1B-Instruct-bnb-4bit is a quantized version of the other (BF16/U8).

1 derivatives checked

• featherless-ai-quants/dat-lequoc-vLLM-fast-apply-16bit-v0.13-Llama3.2-1B-GGUF: Quantization

On the Hub · Downloads on Model Pulse