Versus Engine
NVIDIA RTX Spark Windows PCs vs Radeon RX 9070
Specs, price and the one trade-off that actually decides it — NVIDIA RTX Spark Windows PCs against Radeon RX 9070, side by side.
Cheaper to start
Tie
Both start at a similar price.
Best ecosystem
Tie
Neither lists native integrations.
Standout
NVIDIA RTX Spark Windows PCs
Precision-machined aluminum chassis
NVIDIA RTX Spark Windows PCs
NVIDIA RTX Spark Windows PCs with precision-machined aluminum chassis and tandem OLED displays
Where it wins, where it doesn't
Pros
- Precision-machined aluminum chassis for durability and aesthetic appeal
- Tandem OLED displays with NVIDIA G-SYNC technology for superior visual performance
- Capable of running 120-billion-parameter large language models with 1 million tokens context
Cons
- High price point may limit accessibility for budget-conscious users
Specifications
- achievable frequency—
- ai accelerators—
- Architecture—
- Board Design / Outputs—
- Board Design / Power Connectors—
- Board Design / Suggested PSU—
- Board Design / TDP—
- Bus Interface—
- bus type—
- chassisprecision-machined aluminum chassis
- Chip Package—
- Clock Speeds / Base Clock—
- Clock Speeds / Boost Clock—
- Clock Speeds / Game Clock—
- Clock Speeds / Memory Clock—
- Density—
- Die Size—
- displaytandem OLED displays with NVIDIA G-SYNC technology
- displayport™—
- DLSSedit 12K 4:2:2 video with the NVIDIA Blackwell decoder
- DLSS 4.5 Ray Reconstructionfeaturing a second-generation transformer model
- features—
- Foundry—
- game frequency—
- Generation—
- gpu memory—
- GPU Name—
- GPU Variant—
- Graphics Card—
- Graphics Features / OpenCL—
- Graphics Features / OpenGL—
- Graphics Features / Vulkan—
- hdmi™—
- large language modelsrun 120-billion-parameter large language models with 1 million tokens context
- Matrix Performance / BF16—
- Matrix Performance / INT4—
- Matrix Performance / INT8—
- Matrix Performance / Sparse Matrix—
- max memory size—
- Memory / Bandwidth—
- Memory / Memory Bus—
- Memory / Memory Size—
- memory bandwidth—
- memory interface—
- memory speed—
- memory type—
- Navi 48 GPU Notes—
- Numeric Format Support / Matrix—
- Numeric Format Support / Vector—
- Package Size—
- peak 4-bit precision (int4 matrix) performance—
- peak 8-bit precision (fp8 matrix) performance (e5m2, e4m3)—
- peak 8-bit precision (int8 matrix) performance—
- peak half precision (fp16 matrix) performance—
- peak half precision (fp16 vector) performance—
- peak pixel fill-rate—
- peak single precision (fp32 vector) performance—
- Predecessor—
- Process Size—
- Process Type—
- ray accelerators—
- Render Config / L0 Cache—
- Render Config / L2 Cache—
- Render Config / L3 Cache—
- Render Config / Matrix Cores—
- Render Config / RT Cores—
- Render Config / Shading Units—
- Render Config / TMUs—
- rops—
- RTX Videowith 4x Frame Generation
- size14- to 16-inch sizes
- stream processors—
- Successor—
- supported rendering format—
- Theoretical Performance / FP16—
- Theoretical Performance / FP32—
- Theoretical Performance / FP64—
- Theoretical Performance / Pixel Rate—
- Theoretical Performance / Texture Rate—
- thicknessas slim as 14 millimeters
- transistor count—
- Transistors—
- typical board power (desktop)—
- weightas light as three pounds
Radeon RX 9070
Radeon RX 9070 graphics card with up to 2520 MHz achievable frequency and 16 GB GDDR6 memory
Where it wins, where it doesn't
Pros
- Achievable frequency of up to 2520 MHz
- 16 GB of GDDR6 memory
- Up to 640 GB/s memory bandwidth
Cons
- Requires a minimum PSU of 650W
- High typical board power of 220W
Specifications
- achievable frequencyUp to 2520 MHz
- ai accelerators112
- ArchitectureRDNA 4
- Board Design / Outputs1x HDMI 2.1b, 3x DisplayPort 2.1a
- Board Design / Power Connectors2x 8-pin
- Board Design / Suggested PSU550 W
- Board Design / TDP220 W
- Bus InterfacePCIe 5.0 x16
- bus typePCIe® 5.0 x16
- chassis—
- Chip PackageHFCBGA-2069
- Clock Speeds / Base Clock1330 MHz
- Clock Speeds / Boost Clock2520 MHz
- Clock Speeds / Game Clock2070 MHz
- Clock Speeds / Memory Clock2518 MHz
- Density151.0M / mm²
- Die Size357 mm²
- display—
- displayport™2.1a
- DLSS—
- DLSS 4.5 Ray Reconstruction—
- featuresAMD Software Adrenalin Edition, AMD Fluid Motion Frames, AMD Noise Suppression, AMD Radeon™ Super Resolution, AMD Smart Access Memory, AMD Smart Access Video, AMD Privacy View, AMD Radeon™ Boost, AMD Radeon™ Anti-Lag, AMD Radeon™ Image Sharpening, AMD Enhanced Sync Technology, AMD FreeSync™ Technology, AMD Radeon™ Chill, AMD Virtual Super Resolution, AMD FSR™ 'Redstone'
- FoundryTSMC
- game frequency2070 MHz
- GenerationNavi IV
- gpu memoryAMD Infinity Cache Technology
- GPU NameNavi 48
- GPU VariantNavi 48 XT
- Graphics CardRX 9000
- Graphics Features / OpenCL2.0
- Graphics Features / OpenGL4.6
- Graphics Features / Vulkan1.4
- hdmi™2.1b
- large language models—
- Matrix Performance / BF16144.5 TFLOPS
- Matrix Performance / INT4578.0 TOPS
- Matrix Performance / INT8289.0 TOPS
- Matrix Performance / Sparse Matrix2x Throughput
- max memory size16 GB
- Memory / Bandwidth644.6 GB/s
- Memory / Memory Bus256 bit
- Memory / Memory Size16 GB
- memory bandwidthUp to 640 GB/s
- memory interface256-bit
- memory speedUp to 20 Gbps
- memory typeGDDR6
- Navi 48 GPU NotesSuper Resolution: FSR 4.1.2, XeSS 3, Frame Generation: FSR 4.0.2, XeSS 3, Ray Regeneration: FSR 1.2.1, Radiance Caching: FSR 0.9.0 (Technical Preview), Compute Units: 4th Gen, Ray Tracing: 3rd Gen, Infinity Cache: 3rd Gen, AI Accelerators: 2nd Gen, Radiance Display Engine: 2nd Gen, Shader ISA: GFX12.0 (gfx1201), Graphics/Compute: 12.0.1, Display Core Next: 4.0.1, Video Core Next: 5.0.0, JPEG Engine: 5.0.0
- Numeric Format Support / MatrixINT1, INT2, INT4, INT8, MXFP4, NVFP4, MXFP6, FP8, MXFP8, FP16, BF16, FP32, TF32, FP64
- Numeric Format Support / VectorINT4, INT8, INT16, INT32, FP16, BF16, FP32, FP64
- Package Size45 mm × 35 mm
- peak 4-bit precision (int4 matrix) performance578 TOPs
- peak 8-bit precision (fp8 matrix) performance (e5m2, e4m3)289 TFLOPs
- peak 8-bit precision (int8 matrix) performance289 TOPs
- peak half precision (fp16 matrix) performance145 TFLOPs
- peak half precision (fp16 vector) performance36.1 TFLOPs
- peak pixel fill-rateUp to 322.6 GP/s
- peak single precision (fp32 vector) performance36.1 TFLOPs
- PredecessorNavi III
- Process Size4 nm
- Process TypeN4P FinFET
- ray accelerators56
- Render Config / L0 Cache32 KB per CU
- Render Config / L2 Cache8 MB
- Render Config / L3 Cache64 MB
- Render Config / Matrix Cores112
- Render Config / RT Cores56
- Render Config / Shading Units3584
- Render Config / TMUs224
- rops128
- RTX Video—
- size—
- stream processors3584
- SuccessorAlpha Trion
- supported rendering formatHDMI™ 4K Support, 4K H264 Decode, 4K H264 Encode, H265/HEVC Decode, H265/HEVC Encode, AV1 Decode, AV1 Encode
- Theoretical Performance / FP1636.13 TFLOPS (1:1)
- Theoretical Performance / FP3236.13 TFLOPS
- Theoretical Performance / FP641.129 TFLOPS (1:32)
- Theoretical Performance / Pixel Rate322.6 GPixel/s
- Theoretical Performance / Texture Rate564.5 GTexel/s
- thickness—
- transistor count53.9 B
- Transistors53.9 billion
- typical board power (desktop)220W
- weight—