NVIDIA GeForce RTX 3090 vs Radeon RX 7900 XTX — Specs & Performance Compared
Side-by-side comparison of 2 GPU parts: NVIDIA GeForce RTX 3090 vs Radeon RX 7900 XTX. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.
Verdict: The Radeon RX 7900 XTX is ahead of the NVIDIA GeForce RTX 3090 on all 6 shared benchmarks on file, by 4% to 37% (37% in 3DMark Speed Way). On llama3:70b, the Radeon RX 7900 XTX generates 13.4 tokens/s against 10.0 for the NVIDIA GeForce RTX 3090 (best community run on file for each).
Radeon RX 7900 XTX
*Price sourced from Amazon.com. Price and availability subject to change.
Where to buy
A listing for each part; the current price and stock are on the retailer's page.
Specs side-by-side
| Spec | NVIDIA GeForce RTX 3090 | Radeon RX 7900 XTX |
|---|---|---|
| vram gb | 24 | 24 |
| vram type | GDDR6X | — |
| tdp w | 350 | — |
| cuda cores | 10496 | — |
Synthetic benchmarks
Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Per-row scores come from public benchmark databases (PassMark, TechPowerUp, Geekbench, Cinebench). Empty cells mean we don't yet have that benchmark on file for the SKU.
| Benchmark | NVIDIA GeForce RTX 3090 | Radeon RX 7900 XTX |
|---|---|---|
| 3DMark Port Royal (higher is better) | 15,039 points | 15,715 points |
| 3DMark Speed Way (higher is better) | 5,075 points | 6,953 points |
| 3DMark Steel Nomad (higher is better) | 5,229 points | 6,862 points |
| 3DMark Time Spy (higher is better) | 18,824 points | 25,214 pts |
| 3DMark Time Spy (combined) (higher is better) | — | 27,934 points |
| 3DMark Time Spy (GPU) (higher is better) | — | 30,139 points |
| 3DMark Time Spy Extreme (higher is better) | 9,800 points | — |
| PassMark G2D Mark (higher is better) | 1,069 pts | 1,285 pts |
| PassMark G3D Mark (higher is better) | 26,548 pts | 31,409 pts |
| Port Royal (Ray Tracing) (higher is better) | — | 14,200 pts |
| Tom's Hardware GPU Hierarchy (lower is better) | — | 959 rank |
| Unigine Superposition 4K Optimized (higher is better) | — | 21,192 points |
AI inference (tokens/sec)
Top community-reported tokens-per-second results for popular LLMs. See the per-SKU benchmark page for the full set including quantization, prompt length, and source citations.
NVIDIA GeForce RTX 3090
- llama3.2:1b: 267.0 tok/s
- qwen3:35b-a3b: 135.7 tok/s
- qwen3.6-35b-a3b: 120.0 tok/s
Radeon RX 7900 XTX
- llama2:7b: 170.1 tok/s
- llama3.2:3b: 145.0 tok/s
- llama3.2:3b: 145.0 tok/s
Quick answers
Which is faster, the NVIDIA GeForce RTX 3090 or the Radeon RX 7900 XTX?
The Radeon RX 7900 XTX is ahead of the NVIDIA GeForce RTX 3090 on all 6 shared benchmarks on file, by 4% to 37% (37% in 3DMark Speed Way).
Which is better for running local LLMs?
On llama3:70b, the Radeon RX 7900 XTX generates 13.4 tokens/s against 10.0 for the NVIDIA GeForce RTX 3090 (best community run on file for each).
Keep exploring
More guides & deep dives from the SpecPicks archive
Browse all articles & guides →- Best Budget Gaming PC Build 2026 — ~$1,000 ($800 on Sale)
- The Complete Voodoo5 5500 AGP Driver Guide (2026 Edition)
- Emulation Hardware in 2026: FPGA, Software, and Cart-Reader Ecosystems
- Best 1440p Gaming GPUs in 2026
- Best Retro Handhelds in 2026 — From $35 to $500
- RTX 4070 Super vs RX 7800 XT — Which to Buy in 2026
- How to Build a Windows 98 Retro PC in 2026
More reviews from the SpecPicks archive
Browse all reviews →- Raspberry Pi Zero 2W: Privacy-Preserving Ring Alternative
- Using Claude to Hunt PCI Device IDs on Win98: Voodoo, Audigy, GeForce 4 Ti
- Old RAM Identification: Decode Part Numbers & Specs
- Running Qwen3.5/3.6 with NextN MTP on an RTX 3090 Ti
- Can a Raspberry Pi 4 8GB Run a Local LLM? What Actually Works in 2026
- Best Budget SATA SSD for a Retro PC Build in 2026
- Best SATA SSD for Gaming and Everyday Upgrades in 2026
- Best Sound Card and DAC for Competitive FPS Players in 2026
- Prime Day 2026: Gaming Monitor and Logitech Peripheral Deals to Watch
- Can a Raspberry Pi 4 8GB Run a Local LLM with Ollama?
- Arc A770 16GB vs RTX 3060 12GB for Local Llama 3
- RTX A6000 48GB vs RTX 3090 24GB for Production LLM Inference (2026)
- Ryzen 5 2600 vs Ryzen 5 5600G for CPU-Only Llama 3.2 3B in 2026
- Zero-CPU-Overhead OV7725 Camera Streaming on RP2350
- Noctua-Style Pi 5 NAS Build Goes Viral — Here's the Parts List
- Amstrad CPC Emulator Now Runs on the Raspberry Pi Pico 2
- Crucial BX500 vs SanDisk SSD Plus vs WD Blue: Best Budget SATA SSD for a Boot Drive
- Microsoft and Mistral Sign Multi-Billion Europe AI Infra Deal
- Best Budget 4K Gaming Monitor in 2026
- Best Budget Gaming Peripherals in 2026
- Best Single-Board Computer Project Kits for Beginners (2026)
- NVMe vs SATA for Game Load Times: WD Blue SN550 vs Crucial BX500 in 2026
- The Adder at the Heart of Intel's 8087 Math Coprocessor
- Best Controller for Steam Deck and PC in 2026: 8BitDo vs GameSir vs DualSense
More buying guides from SpecPicks
Browse all buying guides →- Best AM5 Motherboards for 2026
- Best CPUs for Gaming in 2026
- Best 1440p 240Hz Gaming Monitors in 2026
- Best NVMe SSDs for Gaming in 2026
- Best Graphics Cards for Gaming in 2026
- Best Tools for Building and Repairing Retro PCs in 2026
- Best GPUs for Running Local LLMs in 2026
- Best Controllers for PC Gaming in 2026
- Best CPU Coolers for 2026
- Best GPUs for 4K Gaming in 2026
- Best Mechanical Keyboards for Gaming in 2026
- Best External SSDs for Content Creators in 2026
- Best PC Cases for Building in 2026
- Best GPU for Running 27B-32B Local LLMs in 2026
- Best Gaming Mice for 2026
- Best CPUs for Content Creators in 2026
- Best DDR5 RAM for Gaming PCs in 2026
- Best Retro Gaming Consoles & Handhelds for 2026
- Best NVMe External Enclosures for 2026
- Best 4K Monitors for Content Creators in 2026
- Best Gaming Monitors for 2026
Hardware benchmark data on SpecPicks
All benchmarks →- AMD Ryzen 7 5700GE — benchmarks & specs
- Google Coral PCIe Accelerator — benchmarks & specs
- NVIDIA GeForce RTX 4070 Ti SUPER — benchmarks & specs
- Radeon RX 5700 — benchmarks & specs
- GeForce RTX 5050 — benchmarks & specs
- NVIDIA GeForce RTX 3070 — benchmarks & specs
- AMD Ryzen 9 PRO 7940HS — benchmarks & specs
- Apple M3 Pro 12 Core — benchmarks & specs
- NVIDIA GeForce RTX 3060 Ti — benchmarks & specs
- Intel Core i9-12900K — benchmarks & specs
- GRID RTX6000-6Q — benchmarks & specs
- Ryzen 5 3600X — benchmarks & specs
- Intel Arc A380E — benchmarks & specs
- Meta Quest 3 128GB — benchmarks & specs
- AMD Ryzen 3 5300G — benchmarks & specs
- Ryzen 5 7500X3D — benchmarks & specs
- AMD Ryzen 3 7320C — benchmarks & specs
- RTX 5000 Ada Generation — benchmarks & specs
- Arc B370 — benchmarks & specs
- GeForce RTX 4060 Ti 16GB — benchmarks & specs
- AMD Ryzen 9 7940HX — benchmarks & specs
- NVIDIA RTX A2000 12GB — benchmarks & specs
- NVIDIA H100 PCIe 80GB — benchmarks & specs
- Quadro RTX 6000 — benchmarks & specs

