Question 1

Can the GTX 965M run qwen3 8B?

Accepted Answer

qwen3 8B needs about 5.76GB working set (weights 5.2GB + KV cache 0.56GB at 4k context). The GTX 965M offers ~2GB usable — verdict: no. 5.8 GB vs 2 GB usable — does not fit

Question 2

How fast is qwen3 8B on the GTX 965M?

Accepted Answer

~4.3–7.7 tok/s on the GTX 965M. computed roofline: 80.19 GB/s × 0.28–0.50 efficiency window / 5.2GB (Q4_K_M) — bands, never points.

Question 3

What should I run qwen3 8B on instead?

Accepted Answer

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

Can the GTX 965M run qwen3 8B?

Run qwen3 8B on instead