Question 1

Can the Apple M2 run DEEPSEEK-R1 distill 8B?

Accepted Answer

DEEPSEEK-R1 distill 8B needs about 5.4GB working set (weights 4.9GB + KV cache 0.5GB at 4k context). The Apple M2 offers ~6GB usable — verdict: tight. 5.4 of 6 GB usable — keep context modest

Question 2

How fast is DEEPSEEK-R1 distill 8B on the Apple M2?

Accepted Answer

~16–20 tok/s on the Apple M2. computed roofline: 100 GB/s × 0.80–1.00 efficiency window / 4.9GB (Q4_K_M) — bands, never points.

Question 3

What should I run DEEPSEEK-R1 distill 8B on instead?

Accepted Answer

Tesla P100 (16GB, used) runs it fully ($135).

Can the Apple M2 run DEEPSEEK-R1 distill 8B?

Run DEEPSEEK-R1 distill 8B on instead