What hardware runs DeepSeek R1?

DeepSeek R1 is a 671.03B-parameter mixture-of-experts model with 37.55B active parameters (mit license). The open reasoning heavyweight, with famously vivid prose as a side effect. MLA keeps its KV cache absurdly small.

All figures assume an f16 KV cache, a 0.6 GB display reserve on the GPU, and 64 GB of DDR5 system RAM for the offload tiers. Tune these in the calculator.

Minimum VRAM by quant and context

Full-GPU figures: weights + f16 KV cache + overhead. * below our recommended floor of Q3_K_M.

GPU compatibility

Fits on GPUExpert offloadPartial offloadCPU only

Quant guidance

Our floor for DeepSeek R1 is Q3_K_M — below that, quality degrades faster than the VRAM savings are worth (large models tolerate low bpw better than small ones, which is why the floor is lower here). Prefer the highest quant that still lands "Fits on GPU" or “Expert offload” at your context length in the table above.