The Nano only has 4GB VRAM and DS-R1 is 671B FP8 parameters (equivalent to 671GB model size).
You need something with about 800GB to run the full model with context. You'd still need 400GB to even run a half-sized Q4 quant of R1, so there is no reasonable way that it would work.
You need something with about 800GB to run the full model with context. You'd still need 400GB to even run a half-sized Q4 quant of R1, so there is no reasonable way that it would work.