Can a GMKtec EVO-X2 Ryzen AI Max+ 395 128GB run Qwen3.5-9B?
Yes. Qwen3.5-9B needs 11.1GB 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 usable tier.
GMKtec EVO-X2 Ryzen AI Max+ 395 128GB · Qwen3.5-9B · Q8_0
✅ Fits — grade A+
UsablebetaHybrid attention — KV computed as full-cache upper bound · ROCm/Vulkan performance not yet calibrated
weights 9.53 GBKV cache 1.07 GBoverhead 0.48 GBpool 95.5 GBneeds 11.1 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 × Qwen3.5-9B, llama.cpp, 8K context.
| Quant | File size | Fit | Speed tier |
|---|---|---|---|
| Q8_0 | 9.5 GB | Fits · A+ | usable · beta |
| Q6_K | 7.5 GB | Fits · A+ | usable · beta |
| Q5_K_M | 6.6 GB | Fits · A+ | interactive · beta |
| Q4_K_M | 5.7 GB | Fits · A+ | interactive · beta |
Qwen3.5-9B 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.