mlabonne/FineLlama-3.1-8B
Quantization vs unsloth/Meta-Llama-3.1-8B-bnb-4bit. unsloth/Meta-Llama-3.1-8B-bnb-4bit is a quantized version of the other (U8/BF16).
3 derivatives checked
- bartowski/FineLlama-3.1-8B-GGUF: Quantization
- mradermacher/FineLlama-3.1-8B-GGUF: Same weights, converted
- featherless-ai-quants/mlabonne-FineLlama-3.1-8B-GGUF: Quantization