readygpu

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB vs NVIDIA GeForce RTX 5090

For running models locally, priced in the US. At 64k context the first runs 40 models fully in memory, the second 27.

In short

The GMKtec EVO-X2 Ryzen AI Max+ 395 128GB has more memory for models: 128 GB against 32 GB. At 64k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 27; only the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB holds Qwen 3.8 Flash Next. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 7.9× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models). In the US the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs $3,650 at eBay and the NVIDIA GeForce RTX 5090 $4,921 at eBay: the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB is $1,271 cheaper.

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

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB

$3,650

eBay

Add to build
NVIDIA GeForce RTX 5090

$4,921

eBay

Add to build

Specifications

SpecGMKtec EVO-X2 Ryzen AI Max+ 395 128GBNVIDIA GeForce RTX 5090
ChipRyzen AI Max+ 395 (Radeon 8060S)–
Memory bus256-bit512-bit
Memory bandwidth256 GB/s1,792 GB/s
FP16 compute59.4 TFLOPS209 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 5090
Memory–32 GB GDDR7
Board power–575 W
PCIe generation–Gen 5
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 5090
Qwen 3.8 Flash Next3tok/sUD-Q3_K_XLwon't run
MiniMax M2.74tok/sUD-Q2_K_XLwon't run
Qwen 3.8 27B4tok/sQ8_042tok/sUD-Q6_K
Qwen 3.5 122B-A10B9tok/sQ5_K_Moffload
Qwen 3.6 27B4tok/sQ8_041tok/sQ6_K
gpt-oss 120B15tok/sMXFP4won't run
Qwen3 Coder Next15tok/sQ8_0offload
Nemotron 3 Super 120B-A12B10tok/sUD-Q4_K_Moffload
Gemma 4 31B4tok/sQ8_035tok/sQ6_K
Mistral Small 4 119B11tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B19tok/sQ8_0173tok/sUD-Q6_K
Qwen 3.5 27B4tok/sQ8_041tok/sQ6_K
Gemma 4 26B-A4B15tok/sQ8_0117tok/sQ8_0
GLM 4.5 Air3tok/sQ5_K_Moffload
Qwen 3.5 35B-A3B19tok/sQ8_0175tok/sQ6_K
Qwen3 Next 80B-A3B18tok/sQ8_0offload
GLM 4.7 Flash10tok/sQ8_087tok/sQ6_K
Devstral Small 2 24B4tok/sQ8_037tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B22tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B23tok/sQ8_0277tok/sQ4_K_M
gpt-oss 20B21tok/sMXFP4165tok/sMXFP4
Qwen3 Coder 30B-A3B9tok/sQ8_075tok/sQ6_K
Qwen3 32B3tok/sQ8_0offload
Gemma 4 12B10tok/sQ8_079tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_095tok/sQ8_0
Gemma 3 27B4tok/sQ8_040tok/sQ6_K
Mistral Small 3.2 24B4tok/sQ8_037tok/sQ6_K
DeepSeek R1 Distill Qwen 32B3tok/sQ8_0offload
Llama 3.3 70B2tok/sQ8_0won't run
Ministral 3 14B6tok/sQ8_044tok/sQ8_0
Qwen3 14B5tok/sQ8_042tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_061tok/sQ8_0
Qwen3 8B8tok/sQ8_061tok/sQ8_0
Phi-4 14B5tok/sQ8_038tok/sQ8_0
Qwen 3.5 4B21tok/sQ8_0166tok/sQ8_0
Ministral 3 8B8tok/sQ8_061tok/sQ8_0
Granite 4.2 8B7tok/sQ8_055tok/sQ8_0
Gemma 4 E4B14tok/sQ8_0110tok/sQ8_0
LFM2.5 8B-A1B20tok/sQ8_0156tok/sQ8_0
Llama 3.1 8B9tok/sQ6_K73tok/sQ6_K
DeepSeek V4 Flashwon't runwon't run
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 5090?
Choose the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB to run bigger models. Choose the NVIDIA GeForce RTX 5090 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 5090?
At 64k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 27; only the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB holds Qwen 3.8 Flash Next.
Which is faster for local AI, the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB or the NVIDIA GeForce RTX 5090?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 7.9× 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 5090?
In the US the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs $3,650 at eBay and the NVIDIA GeForce RTX 5090 $4,921 at eBay: the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB is $1,271 cheaper.

More comparisons