Question 1

Can the Intel UHD 770 (iGPU) run mistral-nemo 12B?

Accepted Answer

mistral-nemo 12B needs about 7.72GB working set (weights 7.1GB + KV cache 0.62GB at 4k context). The Intel UHD 770 (iGPU) offers ~13.5GB usable — verdict: full. 7.7 GB needed of 13.5 GB usable — headroom for context

Question 2

How fast is mistral-nemo 12B on the Intel UHD 770 (iGPU)?

Accepted Answer

~1.6–4.9 tok/s on the Intel UHD 770 (iGPU). computed roofline: 76.8 GB/s × 0.15–0.45 efficiency window / 7.1GB (Q4_K_M) — bands, never points.

Question 3

What should I run mistral-nemo 12B on instead?

Accepted Answer

Tesla M60 (16GB, used) runs it fully ($35).

Can the Intel UHD 770 (iGPU) run mistral-nemo 12B?

Run mistral-nemo 12B on instead