Llamacpp imatrix Quantizations of Kimi Linear 48B A3B Instruct by moonshotai Using llama.cpp release b7966 for quantization. Original model: https://huggingface.co/moonshotai/Kimi Linear 48B A3B Instruct All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format No prompt format found, check original model page Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Kimi Linear 48B A3B Instruct bf16.gguf bf16 98.29GB true Full BF16 weights. Kimi Linear 48B A3B Instruct Q8 0.gguf Q8 0 52.25GB true Extremely high quality, generally unneeded but max available quant. Kimi Linear 48B A3B Instruct Q6 K L.gguf Q6 K L 40.64GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Kimi Linear 48B A3B Instruct Q6 K.gguf Q6 K 40.46GB false Very high quality, near perfect, recommended . Kimi Linear 48B A3B Instruct Q5 K L.gguf Q5 K L 35.33GB false Uses Q8 0 for embed and output weights. High quality, recomm…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy