RTX 4090 vs RTX 5090
RTX 4090 · 24 GB VRAM and RTX 5090 · 32 GB VRAM side by side for local AI.
Facts from both hardware pages
| Specification | RTX 4090 | RTX 5090 |
|---|---|---|
| Memory | 24 GB VRAMDedicated · system RAM does not add · source | 32 GB VRAMDedicated · system RAM does not add · source |
| Memory bandwidth | 1,008 GB/sManufacturer spec · not model speed · source | 1,792 GB/sManufacturer spec · not model speed · source |
| Text · run well | 129+7 tight fit · 25 run slowly · within 24 GB | 158+2 tight fit · 25 run slowly · within 32 GB |
| Vision · run well | 126+7 tight fit · within 24 GB | 140+2 tight fit · within 32 GB |
| Image · within memory | 53within 24 GB · documented paths and minimums | 64within 32 GB · documented paths and minimums |
| Video · within memory | 30within 24 GB · documented paths and minimums | 34within 32 GB · documented paths and minimums |
| Audio · within memory | 128within 24 GB · documented paths and minimums | 132within 32 GB · documented paths and minimums |
| Embeddings · within memory | 90within 24 GB · 8-bit estimate | 90within 32 GB · 8-bit estimate |
| Published speed runs | 1313 on this machine | 1716 on this machine · 1 naming only the chip |
| Launch price (MSRP) | USD 1,599US · dated 2022-10-12 · not a tracked offer · source | USD 1,999US · dated 2025-01-30 · not a tracked offer · source |
| Where to buy | No manufacturer store link on file | NVIDIA Marketplacethis configuration · US · recorded 2026-10-18 · store link |
Counts use the same memory estimate as each hardware page: text and vision run well within the fast memory (tight fits counted apart); image, video and audio use documented paths and publisher minimums. Formulas
Top text models each runs well
The first 5 rows of each hardware page's Text list, in its order: LiveBench score, then reviewed models, then Hub downloads. Memory is the planning estimate on that machine.
| Rank | RTX 4090 | RTX 5090 |
|---|---|---|
| #1 | Smaug MiniAbacus AI · LiveBench 76.9 · ~23 GB | Smaug MiniAbacus AI · LiveBench 76.9 · ~23 GB |
| #2 | Qwen3.8 27BAlibaba · LiveBench 75.3 · ~23 GB | Qwen3.8 27BAlibaba · LiveBench 75.3 · ~23 GB |
| #3 | Qwen3.6 27BAlibaba · LiveBench 64 · ~23 GB | Qwen3.6 27BAlibaba · LiveBench 64 · ~23 GB |
| #4 | Qwen3 14BAlibaba · ~14 GB | Qwen3 14BAlibaba · ~14 GB |
| #5 | Gemma 4 26B A4BGoogle · ~21 GB | Gemma 4 31BGoogle · ~26 GB |
Measured speed
Published output tokens per second, as measured. A speed is compared only when the same checkpoint, quantization, runtime and lengths ran on both machines themselves; same-chip references are not compared.
All published measurements · RTX 4090
All published measurements · RTX 5090
Verdict
RTX 4090 has 24 GB VRAM and RTX 5090 has 32 GB VRAM: 8 GB more on RTX 5090. By the memory estimate, 129 text models run well on RTX 4090 and 158 on RTX 5090. RTX 5090 lists 1,792 GB/s of memory bandwidth, 1.8× the 1,008 GB/s of RTX 4090 (a manufacturer spec, not a measured speed). In the same published test (gpt-oss 20B Q4_K_M, llama.cpp CUDA), RTX 4090 measured 278 and RTX 5090 393.3 output tokens per second. Launch prices on file: RTX 4090 USD 1,599 (2022-10-12) and RTX 5090 USD 1,999 (2025-01-30). RTX 5090 leads on both facts here: more text models run well and it measured faster in the shared test.
Limits and dates
Model counts are memory estimates, not speed measurements or guaranteed fits; verify runtime and checkpoint support. Bandwidth is the manufacturer's figure. Prices are launch or list prices with their dates, not current offers.
Page updated · Model catalog checked · LiveBench 2026-06-25