Llamacpp imatrix Quantizations of DeepSeek R1 Distill Llama 70B Using llama.cpp release b4514 for quantization. Original model: https://huggingface.co/deepseek ai/DeepSeek R1 Distill Llama 70B All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description DeepSeek R1 Distill Llama 70B Q8 0.gguf Q8 0 74.98GB true Extremely high quality, generally unneeded but max available quant. DeepSeek R1 Distill Llama 70B Q6 K.gguf Q6 K 57.89GB true Very high quality, near perfect, recommended . DeepSeek R1 Distill Llama 70B Q5 K M.gguf Q5 K M 49.95GB true High quality, recommended . DeepSeek R1 Distill Llama 70B Q5 K S.gguf Q5 K S 48.66GB false High quality, recommended . DeepSeek R1 Distill Llama 70B Q4 1.gguf Q4 1 44.31GB false Legacy format, similar performance to Q4 K S but with improved tokens/watt on Apple silicon. DeepSeek R1 Distill Llama 70B Q4 K M.gguf Q4 K M 42.52GB false Good quality, default size for most use cases, recommended . DeepSeek R1 Distill Llama 70B Q4 K S.gguf Q4 K S 40.35GB false Slightly lower quality with more space savings, recommended .…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy