ASUS Ascent GX10 128GB vs GMKtec EVO-X2 Ryzen AI Max+ 395 128GB
For running models locally, priced in Germany. At 32k context the first runs 42 models fully in memory, the second 41.
In short
Both have 128 GB of memory for models; the ASUS Ascent GX10 128GB has 273 GB/s of bandwidth and the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB 256 GB/s. At 32k context the ASUS Ascent GX10 128GB runs 42 of the models we track fully in memory and the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB 41; only the ASUS Ascent GX10 128GB holds GLM 5.3 Flash. On the models both run fully in memory, the ASUS Ascent GX10 128GB is about 1.2× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models).
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | ASUS Ascent GX10 128GB | GMKtec EVO-X2 Ryzen AI Max+ 395 128GB |
|---|---|---|
| Chip | GB10 Grace Blackwell | Ryzen AI Max+ 395 (Radeon 8060S) |
| Memory bus | 256-bit | 256-bit |
| Memory bandwidth | 273 GB/s | 256 GB/s |
| FP16 compute | 62 TFLOPS | 59.4 TFLOPS |
| Software | CUDA | ROCm |
| Unified memory | 128 GB | 128 GB |
| GPU can use by default | 119 GB | 96 GB |
| GPU can use, tuned | 122 GB | 120 GB |
| Operating system | dgx-os | windows |
| Processor | 20-core Arm (GB10) | Ryzen AI Max+ 395 |
| Storage | 1000 GB | 2000 GB |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | ASUS Ascent GX10 128GB | GMKtec EVO-X2 Ryzen AI Max+ 395 128GB |
|---|---|---|
| DeepSeek V4 Flash | 11tok/sUD-Q2_K_XL | 9tok/sUD-Q2_K_XL |
| GLM 5.3 Flash | 11tok/sUD-Q2_K_XL | won't run |
| Qwen 3.8 Flash Next | 3tok/sUD-Q4_K_XL | 3tok/sUD-Q3_K_XL |
| MiniMax M2.7 | 8tok/sUD-Q3_K_M | 7tok/sUD-Q2_K_XL |
| Qwen 3.8 27B | 5tok/sQ8_0 | 5tok/sQ8_0 |
| Qwen 3.5 122B-A10B | 11tok/sQ6_K | 9tok/sQ6_K |
| Qwen 3.6 27B | 6tok/sQ8_0 | 5tok/sQ8_0 |
| gpt-oss 120B | 23tok/sMXFP4 | 20tok/sMXFP4 |
| Qwen3 Coder Next | 20tok/sQ8_0 | 17tok/sQ8_0 |
| Nemotron 3 Super 120B-A12B | 9tok/sUD-Q6_K | 10tok/sUD-Q4_K_M |
| Gemma 4 31B | 5tok/sQ8_0 | 4tok/sQ8_0 |
| Mistral Small 4 119B | 15tok/sUD-Q6_K | 13tok/sUD-Q6_K |
| Qwen 3.6 35B-A3B | 27tok/sQ8_0 | 22tok/sQ8_0 |
| Qwen 3.5 27B | 6tok/sQ8_0 | 5tok/sQ8_0 |
| Gemma 4 26B-A4B | 20tok/sQ8_0 | 17tok/sQ8_0 |
| GLM 4.5 Air | 4tok/sQ8_0 | 4tok/sQ5_K_M |
| Qwen 3.5 35B-A3B | 27tok/sQ8_0 | 22tok/sQ8_0 |
| Qwen3 Next 80B-A3B | 25tok/sQ8_0 | 21tok/sQ8_0 |
| GLM 4.7 Flash | 14tok/sQ8_0 | 12tok/sQ8_0 |
| Devstral Small 2 24B | 6tok/sQ8_0 | 5tok/sQ8_0 |
| Nemotron 3.5 Lightning 30B-A3B | 28tok/sUD-Q6_K_XL | 24tok/sUD-Q6_K_XL |
| gpt-oss 20B | 31tok/sMXFP4 | 26tok/sMXFP4 |
| Kimi Linear 48B-A3B | 29tok/sQ8_0 | 24tok/sQ8_0 |
| Qwen3 Coder 30B-A3B | 16tok/sQ8_0 | 13tok/sQ8_0 |
| Qwen3 32B | 4tok/sQ8_0 | 3tok/sQ8_0 |
| Gemma 4 12B | 13tok/sQ8_0 | 10tok/sQ8_0 |
| Qwen 3.5 9B | 16tok/sQ8_0 | 13tok/sQ8_0 |
| Mistral Small 3.2 24B | 6tok/sQ8_0 | 5tok/sQ8_0 |
| Gemma 3 27B | 5tok/sQ8_0 | 4tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 32B | 4tok/sQ8_0 | 3tok/sQ8_0 |
| Llama 3.3 70B | 2tok/sQ8_0 | 2tok/sQ8_0 |
| Ministral 3 14B | 9tok/sQ8_0 | 7tok/sQ8_0 |
| Qwen3 14B | 8tok/sQ8_0 | 7tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 13tok/sQ8_0 | 10tok/sQ8_0 |
| Qwen3 8B | 13tok/sQ8_0 | 10tok/sQ8_0 |
| Phi-4 14B | 8tok/sQ8_0 | 6tok/sQ8_0 |
| Qwen 3.5 4B | 30tok/sQ8_0 | 25tok/sQ8_0 |
| Ministral 3 8B | 13tok/sQ8_0 | 10tok/sQ8_0 |
| Granite 4.2 8B | 12tok/sQ8_0 | 10tok/sQ8_0 |
| Gemma 4 E4B | 19tok/sQ8_0 | 15tok/sQ8_0 |
| LFM2.5 8B-A1B | 38tok/sQ8_0 | 32tok/sQ8_0 |
| Llama 3.1 8B | 16tok/sQ6_K | 13tok/sQ6_K |
Questions
- Which is better for local AI, the ASUS Ascent GX10 128GB or the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB?
- Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the ASUS Ascent GX10 128GB for speed.
- Which can run bigger models, the ASUS Ascent GX10 128GB or the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB?
- At 32k context the ASUS Ascent GX10 128GB runs 42 of the models we track fully in memory and the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB 41; only the ASUS Ascent GX10 128GB holds GLM 5.3 Flash.
- Which is faster for local AI, the ASUS Ascent GX10 128GB or the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB?
- On the models both run fully in memory, the ASUS Ascent GX10 128GB is about 1.2× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models).