Text model · DeepSeek-R1
DeepSeek R1 requirements
DeepSeek-R1 family · 671B params (Mixture-of-Experts, 37B active) · released Jan 2025. Minimum to run at Q4_K_M: high-memory hardware.
Quantization sizes
| Quantization | Size on disk |
|---|---|
| Q2_K | 281 GB est |
| Q3_K_M | 328 GB est |
| Q4_K_M (default) | 376.66 GB |
| Q5_K_M | 478.1 GB est |
| Q6_K | 550.2 GB est |
| Q8_0 | 712.9 GB est |
| FP16 | 1342 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
ollama run deepseek-r1:671b llama-cli -hf unsloth/DeepSeek-R1-GGUF:Q4_K_M lms get unsloth/DeepSeek-R1-GGUF Which devices can run DeepSeek R1?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
AMD GPUs
FAQ
How much VRAM or RAM does DeepSeek R1 need?
At Q4_K_M, DeepSeek R1 needs about 383.7 GB (weights ~376.66 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~719.9 GB.
Can DeepSeek R1 run on a laptop?
DeepSeek R1 is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.
Is DeepSeek R1 cheaper to run because it is a MoE model?
It is faster, not lighter. DeepSeek R1 activates only 37B of 671B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 671B.
Can I use DeepSeek R1 commercially?
Yes. DeepSeek R1 is licensed MIT, which permits commercial use.
DeepSeek R1, 671B sparse MoE (37B active). Q4_K_M is ~377GB across a 9-file series, beyond any consumer device. unsloth 1.58-bit dynamic quants run in ~140-160GB, so a 192GB Mac Studio can run it slowly. Size from the unsloth GGUF repo, cross-checked against the Ollama 671B tag.
Sources
Memory figures are estimates. See methodology.