Question 1

Can the Adreno X1-85 (Snapdragon X Elite) 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 Adreno X1-85 (Snapdragon X Elite) 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 Adreno X1-85 (Snapdragon X Elite)?

Accepted Answer

~4.8–15 tok/s on the Adreno X1-85 (Snapdragon X Elite). computed roofline: 135.2 GB/s × 0.25–0.80 efficiency window / 7.1GB (Q4_K_M) — bands, never points.

Question 3

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

Accepted Answer

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

Can the Adreno X1-85 (Snapdragon X Elite) run mistral-nemo 12B?

Run mistral-nemo 12B on instead