Hardware
GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB for local LLMs
64 GB system memory. Usable GPU memory in this catalog is AMD VGM dedicated memory, 48 GB.
Memory
64 GB unifiedCatalog fit uses 48 GB dedicated graphics memory from the row note, not the full system pool.
Bandwidth
256 GB/swww.amd.com/en/blogs/2025/faqs-amd-variable-graphics-memory-vram-ai-model-sizes-quantization-mcp-more.htmlPrice
$2,462€2,199
new (idealo, prepayment, incl. shipping)
price as of 17 Oct 2026
idealo.deidealo data 17 Oct 2026 22:53. 64GB/1TB from €2,199 incl. shipping, prepayment. The next offer was €2,229. A further 64GB/1TB listing was €2,249.68. AMD's VGM FAQ says a 64GB Ryzen AI Max+ system allows up to 48 GB dedicated graphics memory, and quotes 256 GB/s. This catalog scores that 48 GB figure. It is AMD's allocation, not a test on this machine. Unified memory is not the same as discrete VRAM.
Parts in the catalog
- GMKtec EVO-X2, Ryzen AI Max+ 395, 64 GB, 1 TB, Windows 11 Pro, as listed on idealo
Which models fit
Estimate at 8,192 tokens, or the model's maximum when that is shorter. full means the formula fits in usable memory. offload means GPU plus system RAM. no means it does not fit. This is not a measured file.
| Model | Q4Q4_K_Mestimate | Q5Q5 (~0.71 bytes/param)estimate | Q8Q8estimate | FP16FP16estimate |
|---|---|---|---|---|
| Llama 3.2 3B | full | full | full | full |
| Llama 3.1 8B | full | full | full | full |
| Mistral 7B v0.3 | full | full | full | full |
| Gemma 2 9B | full | full | full | full |
| Qwen2.5 14B | full | full | full | full |
| Phi-4 14B | full | full | full | full |
| Gemma 2 27B | full | full | full | no |
| Qwen2.5 32B | full | full | full | no |
| Llama 3.3 70B | full | no | no | no |
| Qwen2.5 72B | no | no | no | no |
| DeepSeek-R1-Distill 70B | full | no | no | no |
| NVIDIA Nemotron 3.5 Bolt 74B-A9B | full | no | no | no |
| Reflection Beam 1.0 | no | no | no | no |
| NVIDIA Nemotron 3.5 Super VL | no | no | no | no |
| DeepSeek V4.1 Flash 1017 | no | no | no | no |
| Meta Muse Spark Open | no | no | no | no |
We'll match you with vetted providers
Embed this
Badges cover nine scored GPUs. This machine is not one of them.
Common questions
- Can GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB run Llama 3.3 70B?
- Yes, fully in memory (estimate). Llama 3.3 70B at Q4_K_M needs about 46.0 GB at 8,192 tokens, and GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB has about 48.0 GB usable.
- Which models fit fully on GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB at Q4?
- 11 of 16 models fit fully at Q4 (estimate, 8,192 tokens): Llama 3.2 3B, Llama 3.1 8B, Mistral 7B v0.3, Gemma 2 9B, Qwen2.5 14B, Phi-4 14B, Gemma 2 27B, Qwen2.5 32B, Llama 3.3 70B, DeepSeek-R1-Distill 70B, NVIDIA Nemotron 3.5 Bolt 74B-A9B.
- How fast is GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB (estimate)?
- About 35 tok/s for Llama 3.2 3B at Q4 (estimate, not a benchmark).