Mistral-7B-v0.1-GGUF Quantized version of CodeLlama-7b-Instruct-hf Created using llama.cpp Available Quants Q2_K Q3_K_L Q3_K_M Q3_K_S Q4_0 Q4_K_M Q4_K_S Q5_0 Q5_K_M Q5_K_S Q6_K Q8_0