readygpu

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in Germany. At 32k context the first runs 41 models fully in memory, the second 26.

In short

The GMKtec EVO-X2 Ryzen AI Max+ 395 128GB has more memory for models: 128 GB against 24 GB. At 32k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 41 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 26; only the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 4.5× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models). In Germany the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs 3.700 € at eBay and the NVIDIA GeForce RTX 4090 3.955 € at eBay: the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB is 255 € cheaper.

Updated . Speeds are estimates; how they are worked out.

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB

3.700 €

eBay

Add to build
NVIDIA GeForce RTX 4090

3.955 €

eBay

Add to build

Specifications

SpecGMKtec EVO-X2 Ryzen AI Max+ 395 128GBNVIDIA GeForce RTX 4090
ChipRyzen AI Max+ 395 (Radeon 8060S)–
Memory bus256-bit384-bit
Memory bandwidth256 GB/s1,008 GB/s
FP16 compute59.4 TFLOPS165 TFLOPS
SoftwareROCmCUDA
Unified memory128 GB–
GPU can use by default96 GB–
GPU can use, tuned120 GB–
Operating systemwindows–
ProcessorRyzen AI Max+ 395–
Storage2000 GB–
GPU–GeForce RTX 4090
Memory–24 GB GDDR6X
Board power–450 W
PCIe generation–Gen 4
PCIe lanes–x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelGMKtec EVO-X2 Ryzen AI Max+ 395 128GBNVIDIA GeForce RTX 4090
DeepSeek V4 Flash9tok/sUD-Q2_K_XLwon't run
Qwen 3.8 Flash Next3tok/sUD-Q3_K_XLwon't run
MiniMax M2.77tok/sUD-Q2_K_XLwon't run
Qwen 3.8 27B5tok/sQ8_028tok/sUD-Q5_K_M
Qwen 3.5 122B-A10B9tok/sQ6_Koffload
Qwen 3.6 27B5tok/sQ8_029tok/sQ5_K_M
gpt-oss 120B20tok/sMXFP4won't run
Qwen3 Coder Next17tok/sQ8_0offload
Nemotron 3 Super 120B-A12B10tok/sUD-Q4_K_Mwon't run
Gemma 4 31B4tok/sQ8_029tok/sQ4_K_M
Mistral Small 4 119B13tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B22tok/sQ8_0145tok/sUD-Q4_K_M
Qwen 3.5 27B5tok/sQ8_029tok/sQ5_K_M
Gemma 4 26B-A4B17tok/sQ8_084tok/sUD-Q6_K
GLM 4.5 Air4tok/sQ5_K_Moffload
Qwen 3.5 35B-A3B22tok/sQ8_0146tok/sQ4_K_M
Qwen3 Next 80B-A3B21tok/sQ8_0offload
GLM 4.7 Flash12tok/sQ8_070tok/sQ5_K_M
Devstral Small 2 24B5tok/sQ8_028tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3B24tok/sUD-Q6_K_XLoffload
gpt-oss 20B26tok/sMXFP4116tok/sMXFP4
Kimi Linear 48B-A3B24tok/sQ8_0offload
Qwen3 Coder 30B-A3B13tok/sQ8_074tok/sQ4_K_M
Qwen3 32B3tok/sQ8_0offload
Gemma 4 12B10tok/sQ8_046tok/sQ8_0
Qwen 3.5 9B13tok/sQ8_059tok/sQ8_0
Mistral Small 3.2 24B5tok/sQ8_028tok/sQ5_K_M
Gemma 3 27B4tok/sQ8_028tok/sQ5_K_M
DeepSeek R1 Distill Qwen 32B3tok/sQ8_0offload
Llama 3.3 70B2tok/sQ8_0won't run
Ministral 3 14B7tok/sQ8_032tok/sQ8_0
Qwen3 14B7tok/sQ8_030tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B10tok/sQ8_046tok/sQ8_0
Qwen3 8B10tok/sQ8_046tok/sQ8_0
Phi-4 14B6tok/sQ8_028tok/sQ8_0
Qwen 3.5 4B25tok/sQ8_0112tok/sQ8_0
Ministral 3 8B10tok/sQ8_046tok/sQ8_0
Granite 4.2 8B10tok/sQ8_043tok/sQ8_0
Gemma 4 E4B15tok/sQ8_068tok/sQ8_0
LFM2.5 8B-A1B32tok/sQ8_0140tok/sQ8_0
Llama 3.1 8B13tok/sQ6_K57tok/sQ6_K
GLM 5.3 Flashwon't runwon't run

Questions

Which is better for local AI, the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB or the NVIDIA GeForce RTX 4090?
Choose the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB to spend less.
Which can run bigger models, the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB or the NVIDIA GeForce RTX 4090?
At 32k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 41 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 26; only the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB or the NVIDIA GeForce RTX 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 4.5× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models).
What is the price difference between the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB and the NVIDIA GeForce RTX 4090?
In Germany the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs 3.700 € at eBay and the NVIDIA GeForce RTX 4090 3.955 € at eBay: the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB is 255 € cheaper.

More comparisons