readygpu

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

For running models locally, priced in Canada. At 64k context the first runs 67 models fully in memory, the second 40.

In short

The GMKtec EVO-X2 Ryzen AI Max+ 395 128GB has more memory for models: 128 GB against 24 GB. At 64k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 67 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 40; 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 4090 is about 4.4× as fast as the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB (estimated, median across models). In Canada the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs $5,099 at Amazon and the NVIDIA GeForce RTX 4090 $3,300 at eBay: the NVIDIA GeForce RTX 4090 is $1,799 cheaper.

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

GMKtec EVO-X2 Ryzen AI Max+ 395 128GB

$5,099

Amazon

Add to build
NVIDIA GeForce RTX 4090

$3,300

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
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_029tok/sQ4_K_M
Qwen 3.5 122B-A10B9tok/sQ5_K_Moffload
Qwen 3.6 27B4tok/sQ8_026tok/sQ5_K_M
gpt-oss 120B15tok/sMXFP4won't run
Qwen3 Coder Next15tok/sQ8_0offload
Nemotron 3 Super 120B-A12B8tok/sQ5_K_Mwon't run
Gemma 4 31B4tok/sQ8_0offload
Mistral Small 4 119B11tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B19tok/sQ8_0115tok/sQ4_K_M
Qwen 3.5 27B4tok/sQ8_030tok/sQ4_K_M
Gemma 4 26B-A4B15tok/sQ8_078tok/sUD-Q5_K_M
GLM 4.5 Air3tok/sQ5_K_Mwon't run
Qwen 3.5 35B-A3B19tok/sQ8_0116tok/sQ4_K_M
Qwen3 Next 80B-A3B18tok/sQ8_0offload
GLM 4.7 Flash10tok/sQ8_057tok/sQ4_K_M
Devstral Small 2 24B4tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B22tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B23tok/sQ8_0offload
gpt-oss 20B21tok/sMXFP493tok/sMXFP4
Qwen3 Coder 30B-A3B9tok/sQ8_0offload
Qwen3 32B3tok/sQ8_0offload
Gemma 4 12B10tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_053tok/sQ8_0
Gemma 3 27B4tok/sQ8_028tok/sQ4_K_M
Mistral Small 3.2 24B4tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B3tok/sQ8_0offload
Llama 3.3 70B2tok/sQ8_0won't run
Ministral 3 14B6tok/sQ8_029tok/sQ6_K
Qwen3 14B5tok/sQ8_027tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_034tok/sQ8_0
Qwen3 8B8tok/sQ8_034tok/sQ8_0
Phi-4 14B5tok/sQ8_026tok/sQ5_K_M
Qwen 3.5 4B21tok/sQ8_094tok/sQ8_0
Ministral 3 8B8tok/sQ8_034tok/sQ8_0
Granite 4.2 8B7tok/sQ8_031tok/sQ8_0
Gemma 4 E4B14tok/sQ8_062tok/sQ8_0
LFM2.5 8B-A1B20tok/sQ8_088tok/sQ8_0
Llama 3.1 8B9tok/sQ6_K41tok/sQ6_K
Qwen2.5 0.5B105tok/sQ8_0468tok/sQ8_0
Qwen3.5 0.8B86tok/sQ8_0382tok/sQ8_0
Qwen3.5 2B62tok/sQ5_K_M277tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B37tok/sQ8_0166tok/sQ8_0
MiniCPM5 2B26tok/sQ8_0114tok/sQ8_0
Mellum2.1 12B A2.5B Thinking23tok/sQ8_0103tok/sQ8_0
LFM2.5 2.6B20tok/sQ8_091tok/sQ8_0
LFM2.5 VL 3B20tok/sQ8_091tok/sQ8_0
Kimi VL A3B16tok/smlx-8bit71tok/smlx-8bit
granite vision 4.1 4b16tok/sQ8_070tok/sQ8_0
granite 4.2 3b15tok/sQ8_068tok/sQ8_0
DeepSeek R1 Distill Qwen 7B12tok/sQ8_053tok/sQ8_0
LFM2.5 24B A2B11tok/sQ8_054tok/sQ5_K_M
GLM 4.6V Flash11tok/sQ8_049tok/sQ8_0
GLM 4.1V 9B Thinking10tok/smlx-8bit43tok/smlx-8bit
DeepSeek R1 Distill Llama 8B8tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 25128tok/sQ8_034tok/sQ8_0
DeepSeek R1 Distill Qwen 14B5tok/sQ8_027tok/sQ5_K_M
GLM 4.5V4tok/sQ4_K_Mwon't run
Devstral Small 25074tok/sQ8_0offload
GLM 4.6V4tok/sQ4_K_Mwon't run
Magistral Small 25064tok/sQ8_0offload
Magistral Small 25074tok/sQ8_0offload
Magistral Small 25094tok/sQ8_0offload
granite 4.2 30b3tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B2tok/sQ8_0won't run
Mistral Medium 3.5 128B1tok/sQ4_K_Mwon't run
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.7won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won'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 NVIDIA GeForce RTX 4090 to spend less.
Which can run bigger models, the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB or the NVIDIA GeForce RTX 4090?
At 64k context the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB runs 67 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 40; 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 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 4.4× 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 Canada the GMKtec EVO-X2 Ryzen AI Max+ 395 128GB costs $5,099 at Amazon and the NVIDIA GeForce RTX 4090 $3,300 at eBay: the NVIDIA GeForce RTX 4090 is $1,799 cheaper.

More comparisons