TokenAssemble

Can a GMKtec EVO-X2 Ryzen AI Max+ 395 128GB run Qwen3-32B?

Yes. Qwen3-32B needs 37.5GB at Q8_0 with llama.cpp and 8K context; the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB has 128GB of unified memory (~75% GPU-addressable) (95.5GB usable) — grade A+, with decode speed in the painful tier.

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB · Qwen3-32B · Q8_0

Fits — grade A+

PainfulbetaROCm/Vulkan performance not yet calibrated
weights 34.8 GBKV cache 2.15 GBoverhead 0.52 GBpool 95.5 GBneeds 37.5 GB

assumes llama.cpp · batch 1 · 8K context · fp16 KV cache

$3,399.99 MSRP · as of 2026-07-11

Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.

Every quant, graded

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB × Qwen3-32B, llama.cpp, 8K context.

QuantFile sizeFitSpeed tier
Q8_034.8 GBFits · A+painful · beta
Q6_K26.9 GBFits · A+painful · beta
Q5_K_M23.2 GBFits · A+painful · beta
Q4_K_M19.8 GBFits · A+painful · beta

Qwen3-32B on similar hardware

More models on the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB

Verdict computed from published specs and measured GGUF file sizes — see how the math works.