Llamacpp imatrix Quantizations of Step 3.7 Flash by stepfun ai Using llama.cpp release b9481 for quantization. Original model: https://huggingface.co/stepfun ai/Step 3.7 Flash All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp ramalama 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 Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Step 3.7 Flash Q8 0.gguf Q8 0 212.00GB true Extremely high quality, generally unneeded but max available quant. Step 3.7 Flash Q6 K L.gguf Q6 K L 172.01GB true Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Step 3.7 Flash Q6 K.gguf Q6 K 171.76GB true Very high quality, near perfect, recommended . Step 3.7 Flash Q5 K L.gguf Q5 K L 142.36GB true Uses Q8 0 for embed and output weights. High quality, recommended . Step 3.7 Flash Q5 K M.gguf Q5 K M 142.03GB true High quality, recommended . Step 3.7 Flash Q5 K S.gguf Q5 K S 137.45GB true High quality, recommended . Step 3.7 Flash Q4 1.gguf Q4 1 125.28GB t…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy