DeepSeek-R1 IQ3_M

llama-cli -hf bartowski/DeepSeek-R1-GGUF:IQ3_M

Downloads and runs in one step, resolving the quantization by name.

hf download bartowski/DeepSeek-R1-GGUF --include "DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-*-of-*.gguf"

This quantization is split across 8 files totalling 272.03 GiB. You need every part — the first is not a smaller version of the model.

• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00001-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00002-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00003-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00004-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00005-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00006-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00007-of-00008.gguf
• DeepSeek-R1-IQ3_M/DeepSeek-R1-IQ3_M-00008-of-00008.gguf

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.