NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5090 — Specs & Performance Compared
Verdict: The NVIDIA GeForce RTX 5090 is ahead of the NVIDIA GeForce RTX 4090 on all 4 shared benchmarks on file, by 2% to 60%, including 60% in 3DMark Port Royal (41,238 vs 25,820). On qwen3:32b, the NVIDIA GeForce RTX 4090 generates 650.0 tokens/s (per Spheron Blog) against 61.4 for the NVIDIA GeForce RTX 5090 (per Hardware Corner), best community run on file for each.
Side-by-side GPU comparison of the NVIDIA GeForce RTX 4090 and the NVIDIA GeForce RTX 5090. Released 2022 (NVIDIA GeForce RTX 4090), 2025 (NVIDIA GeForce RTX 5090). MSRP range: $1,599 · $1,999. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.
NVIDIA GeForce RTX 5090
*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 4090 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| vram gb | 24 | 32 |
| vram type | GDDR6X | GDDR7 |
| tdp w | 450 | 575 |
| cuda cores | 16384 | 21760 |
Synthetic benchmarks
Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Scores come from TechPowerUp, HWBOT, 3DMark, Overclock3D, HWCooling.net, Overclocking.com, LanOC Reviews, The FPS Review, UL Benchmarks, Tom's Hardware, Club386, [H]ard|Forum RTX 4090 Time Spy Thread and Puget Systems; each row links its sources, and where they differ the cell shows their median. Empty cells mean we don't yet have that benchmark on file for the SKU.
| Benchmark | NVIDIA GeForce RTX 4090 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| 3DMark Port Royal (higher is better) Source: TechPowerUp, HWBOT, 3DMark, Overclock3D, HWCooling.net |
25,820 points | 41,238 points |
| 3DMark Speed Way (higher is better) Source: Overclocking.com, 3DMark, LanOC Reviews |
10,527 points | 14,457 points |
| 3DMark Steel Nomad (higher is better) Source: The FPS Review, 3DMark, UL Benchmarks, LanOC Reviews |
27,805 points | 13,050 points |
| 3DMark Steel Nomad (4K) (higher is better) Source: Tom's Hardware |
— | 14,133 points |
| 3DMark Steel Nomad (DX12) (higher is better) Source: Club386 |
93 fps | — |
| 3DMark Steel Nomad (Vulkan) (higher is better) Source: Club386 |
103 fps | — |
| 3DMark Steel Nomad Light (higher is better) Source: The FPS Review |
11,287 points | — |
| 3DMark Time Spy (higher is better) Source: TechPowerUp, [H]ard|Forum RTX 4090 Time Spy Thread, 3DMark |
37,979 points | 39,365 pts |
| 3DMark Time Spy Extreme (higher is better) Source: TechPowerUp, The FPS Review |
29,321 pts | — |
| 3DMark Time Spy Extreme (Graphics) (higher is better) Source: TechPowerUp |
19,000 pts | — |
| 3DMark Time Spy GPU (higher is better) Source: TechPowerUp |
35,200 pts | — |
| Deep Learning Benchmark (ResNet-50) (higher is better) Source: Puget Systems |
128,000 images/sec | — |
AI inference (tokens/sec)
Top community-reported tokens-per-second results for popular LLMs whose weights fit the card's memory, each linked to its source. See the per-SKU benchmark page for the full set including quantization and prompt length.
NVIDIA GeForce RTX 4090
- llama3.1:8b: 2550.0 tok/s (Spheron Blog)
- qwen3:32b: 650.0 tok/s (Spheron Blog)
- llama3:8b: 440.0 tok/s (LocalLLaMA)
NVIDIA GeForce RTX 5090
- Qwen2.5-Coder-7B-Instruct: 5841.0 tok/s (Runpod)
- Llama 3.1 8B FP8: 420.0 tok/s (Runpod)
- gpt-oss:20b: 298.2 tok/s (Hardware Corner)
Quick answers
Which is faster, the NVIDIA GeForce RTX 4090 or the NVIDIA GeForce RTX 5090?
The NVIDIA GeForce RTX 5090 is ahead of the NVIDIA GeForce RTX 4090 on all 4 shared benchmarks on file, by 2% to 60%, including 60% in 3DMark Port Royal (41,238 vs 25,820).
Which is better for running local LLMs?
On qwen3:32b, the NVIDIA GeForce RTX 4090 generates 650.0 tokens/s (per Spheron Blog) against 61.4 for the NVIDIA GeForce RTX 5090 (per Hardware Corner), best community run on file for each.
What did the NVIDIA GeForce RTX 4090 and the NVIDIA GeForce RTX 5090 cost at launch?
The NVIDIA GeForce RTX 4090 launched at a $1,599 MSRP and the NVIDIA GeForce RTX 5090 at $1,999. Street prices drift from launch pricing; the Where to buy section links current listings.
Keep exploring
More guides & deep dives from the SpecPicks archive
Browse all articles & guides →- Best Retro Handhelds in 2026 — From $35 to $500
- Best 1440p Gaming GPUs in 2026
- RTX 4070 Super vs RX 7800 XT — Which to Buy in 2026
- Emulation Hardware in 2026: FPGA, Software, and Cart-Reader Ecosystems
- How to Build a Windows 98 Retro PC in 2026
- Best Budget Gaming PC Build 2026 — ~$1,000 Parts List
- The Complete Voodoo5 5500 AGP Driver Guide (2026 Edition)
More reviews from the SpecPicks archive
Browse all reviews →- Qwen3 0.6B: Raspberry Pi 4 8GB vs Ryzen 5 5600G for Tiny-Model Hosts (2026)
- Best Storage Upgrades for Retro and Budget PC Builds in 2026
- Noctua NH-U12S vs DeepCool AK620 for the Ryzen 7 5800X
- Best CPU for the MSI RTX 3060 12GB: 5600G vs 5700X vs 5800X
- Mount a 90s CD-ROM on Windows 98 Without a CD Drive (2026)
- KOORUI 27" 4K vs Samsung Odyssey 4K for Console + PC Gaming
- Best Parts for a CPU-Offload Local LLM Build in 2026
- IPEX-LLM + Ollama in Docker: Running Local Models on Intel GPUs
- Running Qwen3.6 35B A3B at 80 tok/s on a 12GB GPU: The MTP Setup Guide
- Benchmarking Open LLMs for Tool-Use: RTX 3060 12GB vs Ryzen 5800X CPU-Only
- HiDream-O1 1.5 Lands #3 in Text-to-Image: Can You Run It Locally on a 12GB GPU?
- llama.cpp vs vLLM for Single-User Local Chat on a 12GB GPU (2026)
- Crucial BX500 vs Samsung 870 EVO: Best 1TB SATA SSD for Game Storage
- Open WebUI vs LM Studio: Best Local Chat Front-End for a 12GB GPU
- A LEGO Castle Case for the Raspberry Pi 5 Is Going Viral — Here's the Build
- Tesla P40 vs RTX 3090: Used 24GB GPUs for Local LLMs in 2026
- CompactFlash as a Hard Drive: The Win98 Retro Storage Guide
- Best SATA SSD for the PS4 Pro in 2026 (Cheap Speed Upgrade)
- Adafruit's Cyberdeck Raspberry Pi Music Workstation Guide Lands
- Can You Build an $800 Gaming PC in 2026? Parts + Cost
- Intel Arc A770 16GB for Local LLMs: 2025–2026 Guide
- Retro Game Emulator Online: Top Browser-Based Picks for 2026
- Best GPU for an AI rig in 2026 — the shortlist
- Sound Blaster Audigy 2 ZS Won't Install on Windows XP: Driver Hunt + Fix
More buying guides from SpecPicks
Browse all buying guides →- Best CPUs for Gaming in 2026
- Best Gaming Monitors for 2026
- Best 4K Monitors for Content Creators in 2026
- Best Retro Gaming Consoles & Handhelds for 2026
- Best Tools for Building and Repairing Retro PCs in 2026
- Best NVMe SSDs for Gaming in 2026
- Best PC Cases for Building in 2026
- Best CPU Coolers for 2026
- Best DDR5 RAM for Gaming PCs in 2026
- Best Gaming Mice for 2026
- Best GPUs for Running Local LLMs in 2026
- Best CPUs for Content Creators in 2026
- Best NVMe External Enclosures for 2026
- Best GPU for Running 27B-32B Local LLMs in 2026
- Best Controllers for PC Gaming in 2026
- Best Mechanical Keyboards for Gaming in 2026
- Best Graphics Cards for Gaming in 2026
- Best GPUs for 4K Gaming in 2026
- Best External SSDs for Content Creators in 2026
- Best 1440p 240Hz Gaming Monitors in 2026
- Best AM5 Motherboards for 2026
Hardware benchmark data on SpecPicks
All benchmarks →- NVIDIA H100 PCIe 80GB — benchmarks & specs
- Ryzen 5 3500X — benchmarks & specs
- AMD Ryzen 5 7400 — benchmarks & specs
- AMD Ryzen 7 PRO 5755G — benchmarks & specs
- AMD Ryzen 5 7600X3D — benchmarks & specs
- AMD Ryzen 7 7435H — benchmarks & specs
- Radeon RX 9060 — benchmarks & specs
- Radeon RX 9070 XT — benchmarks & specs
- Ryzen 7 3700X — benchmarks & specs
- AMD Ryzen 9 5900H — benchmarks & specs
- Apple M4 Max 16 Core — benchmarks & specs
- AMD Ryzen 3 7335U — benchmarks & specs
- Radeon RX 6650 XT — benchmarks & specs
- Quadro RTX 5000 — benchmarks & specs
- Intel Core i7-13700K — benchmarks & specs
- Ryzen 7 7800X3D — benchmarks & specs
- NVIDIA RTX A4500 20GB — benchmarks & specs
- NVIDIA Jetson AGX Orin 32GB — benchmarks & specs
- AMD Ryzen Threadripper PRO 7985WX — benchmarks & specs
- Quadro RTX 5000 (Mobile) — benchmarks & specs
- NVIDIA RTX PRO 5000 Blackwell — benchmarks & specs
- AMD Ryzen 7 5800HS — benchmarks & specs
- GeForce RTX 4060 — benchmarks & specs
- AMD Ryzen 5 5600H — benchmarks & specs

