GMKtec EVO-X2 (Ryzen AI Max+ 395) for local AI.
With 128 GB it runs Qwen3.8 27B (needs 22.7 GB). 90 models fit. Published speed: gpt-oss-120b at 46.05 tokens/sec.
Memory64 / 128 GB
Shared between CPU and graphics.
Bandwidth256 GB/s
Higher means faster answers.
PriceFrom about $2,200
As of 2026-10-15. Check before buying.
By memory option.
| Memory | Usable | Models that fit | Best three |
|---|---|---|---|
| 64 GB | 48 GB | 77 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
| 128 GB | 96 GB | 90 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
Published speeds.
Measured by others, with sources. Not our tests.
| Model | Tokens/sec | Engine | Setup | Source |
|---|---|---|---|---|
| gpt-oss-120b | 46.05 | llama.cpp ROCm (llama-bench) · MXFP4 (GGUF) | EVO-X2 128GB, Ubuntu 24.04 (Nish Tahir, 2025-10-23) | community-measured · 2026-10-15 |
Short answers.
- What is the best local LLM for the GMKtec EVO-X2 (Ryzen AI Max+ 395)?
- With 128 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 90 of 124 models fit. With 64 GB: Qwen3.8 27B.
- How fast is the GMKtec EVO-X2 (Ryzen AI Max+ 395) for local AI?
- Published: gpt-oss-120b at 46.05 tokens/sec (llama.cpp ROCm (llama-bench), EVO-X2 128GB, Ubuntu 24.04 (Nish Tahir, 2025-10-23)). These are other people's measurements, not ours.
- How much does the GMKtec EVO-X2 (Ryzen AI Max+ 395) cost?
- From about $2,200 (as of 2026-10-15). 2026 prices are inflated by the memory-chip shortage; check before buying.
Specs from OpenClaw DC – Is a Strix Halo mini PC worth $3,500 (prices 2026-09-23; 256 GB/s arithmetic) (2026-09-23). Prices are approximate and dated; 2026 prices are inflated by the memory-chip shortage.
# GMKtec EVO-X2 (Ryzen AI Max+ 395) for local AI URL: https://insidethemachine.ai/machines/gmktec-evo-x2 Type: AMD mini PC. Chip: AMD Ryzen AI Max+ 395 (Strix Halo). Memory: unified, options 64, 128 GB. Bandwidth: 256 GB/s. Spec source: https://openclawdc.com/blog/is-a-strix-halo-mini-pc-worth-it/ (2026-09-23). Price: from about $2,200 (2026-10-15, approximate). Status: current. ## Which models fit | memory GB | usable GB | models that fit | best 3 | |---|---|---|---| | 64 | 48 | 77 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) | | 128 | 96 | 90 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) | ## Published speeds (not our tests) - gpt-oss-120b: 46.05 tok/s decode, 818.11 tok/s prompt (llama.cpp ROCm (llama-bench), MXFP4 (GGUF), EVO-X2 128GB, Ubuntu 24.04 (Nish Tahir, 2025-10-23), community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15) ## Questions **What is the best local LLM for the GMKtec EVO-X2 (Ryzen AI Max+ 395)?** With 128 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 90 of 124 models fit. With 64 GB: Qwen3.8 27B. **How fast is the GMKtec EVO-X2 (Ryzen AI Max+ 395) for local AI?** Published: gpt-oss-120b at 46.05 tokens/sec (llama.cpp ROCm (llama-bench), EVO-X2 128GB, Ubuntu 24.04 (Nish Tahir, 2025-10-23)). These are other people's measurements, not ours. **How much does the GMKtec EVO-X2 (Ryzen AI Max+ 395) cost?** From about $2,200 (as of 2026-10-15). 2026 prices are inflated by the memory-chip shortage; check before buying.