LobnaSellami7/SC_16bit_merged_ready_final_finetuned_model

Quantization vs unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).

1 derivatives checked

• featherless-ai-quants/LobnaSellami7-SC_16bit_merged_ready_final_finetuned_model-GGUF: Quantization

On the Hub · Downloads on Model Pulse