Versus Engine
GMKtec EVO-X2 (128GB) vs Radeon RX 9070 XT
Specs, price and the one trade-off that actually decides it — GMKtec EVO-X2 (128GB) against Radeon RX 9070 XT, side by side.
Cheaper to start
Tie
Both start at a similar price.
Rated higher
GMKtec EVO-X2 (128GB)
8.0 vs 0.0 on our design scale.
Standout
GMKtec EVO-X2 (128GB)
128GB massive memory pool

GMKtec EVO-X2 (128GB)
Enthusiast-tier mini workstation: AMD Ryzen AI Max+ 395 with 128 GB of unified memory. Runs Llama 3.3 70B and Mistral Small 3.1 at roughly 15-25 tokens/s — 70B-class models without a discrete GPU, in a small-form-factor chassis.
Where it wins, where it doesn't
Pros
- 128GB massive memory pool
- Ultra-compact form factor
- Dual NVMe storage slots
Cons
- APU graphics bottleneck token generation speed
- Audible fan noise under sustained load
Specifications
- displayportDisplayPort 1.4 ×1, up to 8K@60Hz
- hdmiHDMI 2.1 ×1, up to 8K@60Hz
- memory_speed8000MHz
- 4K H264 Decode—
- 4K H264 Encode—
- ai_npuBased on AMD XDNA 2 architecture; AI TOPS performance varies by application, model, and settings
- audio3.5mm headphone / audio jack ×1
- AV1 Decode—
- AV1 Encode—
- Bandwidth—
- bluetoothBluetooth 5.4
- Boost Clock—
- Bus Interface—
- Bus Type—
- chipAMD Ryzen AI Max+ 395
- Chip Package—
- Compute Units—
- Density—
- Die Size—
- dimensionsApproximately 186 × 77 × 192 mm
- DirectX—
- Display Core Next—
- display_outputHDMI 2.1 ×1, DisplayPort 1.4 ×1, USB4 ×2, supports up to 8K@60Hz display output, actual output depends on display, cables, and settings
- example_modelsLlama 3.3 70B, Mistral Small 3.1
- FP16—
- FP32—
- FP64—
- FP8—
- FSR—
- Generation—
- GPU Memory—
- Graphics Card—
- H265/HEVC Decode—
- H265/HEVC Encode—
- Infinity Cache—
- INT4—
- INT8—
- L0 Cache—
- L2 Cache—
- L3 Cache—
- Matrix Cores—
- Max Memory Size—
- memory128GB LPDDR5X 8000MHz
- Memory Bandwidth—
- Memory Bus—
- Memory Clock—
- Memory Interface—
- Memory Size—
- Memory Type—
- memory_capacity128GB LPDDR5X
- memory_formOnboard LPDDR5X, typically not user-upgradeable
- Minimum PSU Recommendation—
- nameGMKtec EVO-X2 AMD Ryzen AI Max+ 395 128GB RAM + 2TB SSD Windows 11 Pro Mini PC 2 years warranty (CS-GEVOX2)
- OpenCL—
- OpenGL—
- operating_systemWindows 11 Pro
- Outputs—
- Package Size—
- Pixel Rate—
- Power Connectors—
- Predecessor—
- preloaded_storage2TB M.2 2280 SSD
- processorAMD Ryzen™ AI Max+ 395, 16 cores / 32 threads, up to 5.1GHz
- Radiance Display Engine—
- Ray Tracing—
- ROPs—
- RT Cores—
- sd_card_readerSome official / retail data indicates SD Card Reader, actual shipping version varies
- Shader ISA—
- skuCS-GEVOX2
- Slot Width—
- storage2TB M.2 2280 SSD; up to 2 M.2 2280 slots for expansion, actual capacity depends on SKU and hardware support
- storage_expansionUp to 2 M.2 2280 slots; expansion limit depends on actual unit and manufacturer data
- Stream Processors—
- Successor—
- Suggested PSU—
- Texture Rate—
- tierenthusiast
- TMUs—
- tokens_per_second15-25
- TPP—
- TPP Density—
- Transistor Count—
- Typical Board Power (Desktop)—
- unified_memory_gb128
- usb_aUSB 3.2 ×3, USB 2.0 ×2
- Video Core Next—
- Vulkan—
- warranty2 years
- wired_network2.5G LAN ×1
- wireless_networkWi-Fi 7
Radeon RX 9070 XT
High-performance Radeon RX 9070 XT graphics card with 4096 stream processors and up to 304W typical board power.
Where it wins, where it doesn't
Pros
- Supports multiple video decoding and encoding formats
- High memory bandwidth up to 640 GB/s
- 16 GB GDDR6 memory for large data sets
Cons
- Requires a minimum 750W power supply
- High typical board power of 304W increases cooling demands
Specifications
- displayport2.1a
- hdmi2.1b
- memory_speedUp to 20 Gbps
- 4K H264 DecodeYes
- 4K H264 EncodeYes
- ai_npu—
- audio—
- AV1 DecodeYes
- AV1 EncodeYes
- Bandwidth644.6 GB/s
- bluetooth—
- Boost Clock2970 MHz
- Bus InterfacePCIe 5.0 x16
- Bus TypePCIe® 5.0 x16
- chip—
- Chip PackageHFCBGA-2069
- Compute Units64
- Density151.0M / mm²
- Die Size357 mm²
- dimensions—
- DirectX12 Ultimate (12_2)
- Display Core Next4.0.1
- display_output—
- example_models—
- FP1648.66 TFLOPS (1:1)
- FP3248.66 TFLOPS
- FP641.521 TFLOPS (1:32)
- FP8389.3 TFLOPS
- FSR4.1.2, XeSS 3
- GenerationNavi IV
- GPU MemoryAMD Infinity Cache Technology
- Graphics CardRX 9000
- H265/HEVC DecodeYes
- H265/HEVC EncodeYes
- Infinity Cache3rd Gen
- INT4778.6 TOPS
- INT8389.3 TOPS
- L0 Cache32 KB per CU
- L2 Cache8 MB
- L3 Cache64 MB
- Matrix Cores128
- Max Memory Size16 GB
- memory—
- Memory BandwidthUp to 640 GB/s
- Memory Bus256 bit
- Memory Clock2518 MHz
- Memory Interface256-bit
- Memory Size16 GB
- Memory TypeGDDR6
- memory_capacity—
- memory_form—
- Minimum PSU Recommendation750W
- name—
- OpenCL2.0
- OpenGL4.6
- operating_system—
- Outputs1x HDMI 2.1b 3x DisplayPort 2.1a
- Package Size45 mm × 35 mm
- Pixel Rate380.2 GPixel/s
- Power Connectors2x 8-pin
- PredecessorNavi III
- preloaded_storage—
- processor—
- Radiance Display Engine2nd Gen
- Ray Tracing3rd Gen
- ROPs128
- RT Cores64
- sd_card_reader—
- Shader ISAGFX12.0 (gfx1201)
- sku—
- Slot WidthDual-slot
- storage—
- storage_expansion—
- Stream Processors4096
- SuccessorAlpha Trion
- Suggested PSU700 W
- Texture Rate760.3 GTexel/s
- tier—
- TMUs256
- tokens_per_second—
- TPP3114
- TPP Density9.06
- Transistor Count53.9 B
- Typical Board Power (Desktop)304W
- unified_memory_gb—
- usb_a—
- Video Core Next5.0.0
- Vulkan1.4
- warranty—
- wired_network—
- wireless_network—
