Question 1

Can the AMD Ryzen AI Max (Strix Halo) run qwen3 8B?

Accepted Answer

qwen3 8B needs about 5.76GB working set (weights 5.2GB + KV cache 0.56GB at 4k context). The AMD Ryzen AI Max (Strix Halo) offers ~30GB usable — verdict: full. 5.8 GB needed of 30 GB usable — headroom for context

Question 2

How fast is qwen3 8B on the AMD Ryzen AI Max (Strix Halo)?

Accepted Answer

~30–42 tok/s on the AMD Ryzen AI Max (Strix Halo). computed roofline: 256 GB/s × 0.60–0.85 efficiency window / 5.2GB (Q4_K_M) — bands, never points.

Question 3

What should I run qwen3 8B on instead?

Accepted Answer

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

Can the AMD Ryzen AI Max (Strix Halo) run qwen3 8B?

Run qwen3 8B on instead