Question 1

Can the AMD Radeon RX 6600 XT 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 AMD Radeon RX 6600 XT offers ~8GB usable — verdict: tight. 7.7 of 8 GB usable — keep context modest

Question 2

How fast is mistral-nemo 12B on the AMD Radeon RX 6600 XT?

Accepted Answer

~16–26 tok/s on the AMD Radeon RX 6600 XT. computed roofline: 256 GB/s × 0.45–0.72 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 AMD Radeon RX 6600 XT run mistral-nemo 12B?

Run mistral-nemo 12B on instead