Question 1

Can the NVIDIA RTX A6000 run DEEPSEEK-R1 distill 7B?

Accepted Answer

DEEPSEEK-R1 distill 7B needs about 4.92GB working set (weights 4.7GB + KV cache 0.22GB at 4k context). The NVIDIA RTX A6000 offers ~48GB usable — verdict: full. 4.9 GB needed of 48 GB usable — headroom for context

Question 2

How fast is DEEPSEEK-R1 distill 7B on the NVIDIA RTX A6000?

Accepted Answer

~75–120 tok/s on the NVIDIA RTX A6000. computed roofline: 768 GB/s × 0.46–0.76 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Question 3

What should I run DEEPSEEK-R1 distill 7B on instead?

Accepted Answer

Raspberry Pi 5 + AI Kit (Hailo-8L) runs it fully ($110).

Can the NVIDIA RTX A6000 run DEEPSEEK-R1 distill 7B?

Run DEEPSEEK-R1 distill 7B on instead