NVIDIA GeForce RTX 4090, AI & Machine Learning Benchmarks & Specs

24GB · AI Score 10.4/100 · first-party measured on 12 AI workloads

10.4 AI Score ✓ Measured

Every number on this page is first-party: NVIDIA GeForce RTX 4090 was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) NVIDIA GeForce RTX 4090 delivers about 171.29 tokens/sec. Stepping up to Qwen3 32B it holds roughly 44.28 tok/s. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 24GB. For image generation, SDXL runs at 8.14 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 4 of the 12 workloads won't fit on 24GB at the tested precision, Llama 3.3 70B, FLUX.1-dev, FLUX.1 Kontext, Qwen-Image-Edit. We publish those as hard gates rather than quietly dropping to a smaller quant. NVIDIA GeForce RTX 4090 isn't a retail purchase for most people. It's rented by the hour. You can run this exact card on RunPod.

Bench notes: from the person who ran it

Best consumer efficiency I measured, period: 2.24 tokens/watt on Qwen3 4B. It'll take its full 450W on SDXL and stay under 68°C. The one thing people get wrong: 24GB still can't hold Llama 3.3 70B: that model wants ~46GB, and no consumer card changes that. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.

AI & Machine Learning benchmark results

Text Generation tok/s 5

Qwen3 4B260.54
Llama 3.1 8B171.29
Qwen2.5-Coder 14B95.12
Qwen3 32B44.28
WorkloadResultTelemetryData
Qwen3 4B260.54 tok/s
3.1 GB peak116 W38°C2.24 tok/WQ4_K_M
✓ Measured
Llama 3.1 8B171.29 tok/s
5.1 GB peak191 W42°C0.9 tok/WQ4_K_M
✓ Measured
Qwen2.5-Coder 14B95.12 tok/s
8.5 GB peak174 W46°C0.55 tok/WQ4_K_M
✓ Measured
Qwen3 32B44.28 tok/s
18.9 GB peak164 W47°C0.27 tok/WQ4_K_M
✓ Measured
Llama 3.3 70B✕ Won't fit needs ~46 GBVRAM-gated at this precision✓ Measured

Image Generation images/min 3

WorkloadResultTelemetryData
Stable Diffusion XL16.28 images/min
14.8 GB peak421 W53°C3.7 s/img
✓ Measured
Z-Image Turbo7.43 images/min
23.3 GB peak425 W58°C8.1 s/img
✓ Measured
FLUX.1 dev✕ Won't fit needs ~26 GBVRAM-gated at this precision✓ Measured

Image Editing images/min 2

WorkloadResultTelemetryData
FLUX.1 Kontext dev✕ Won't fit needs ~26 GBVRAM-gated at this precision✓ Measured
Qwen-Image-Edit✕ Won't fit needs ~42 GBVRAM-gated at this precision✓ Measured

Video Generation frames/s 2

WorkloadResultTelemetryData
LTX-Video (distilled)4.7 frames/s
9.4 GB peak269 W55°C20.6 s/clip
✓ Measured
Wan 2.2 5B (720p)0.43 frames/s
18.6 GB peak366 W68°C114.5 s/clip
✓ Measured
How we measured this. Every result comes from our own pinned, reproducible AI suite, 12 workloads: the Qwen3-4B to Llama-70B LLM ladder (llama.cpp, Q4_K_M), SDXL / Z-Image / FLUX-dev generation, FLUX-Kontext / Qwen-Edit editing, and LTX / Wan video, run first-party on rented hardware with under 0.5% run-to-run variance. Peak VRAM, power draw, temperature and tokens-per-watt are captured per workload. “Won’t fit” rows are real data: where a model exceeds the card’s VRAM at the tested precision we record a hard gate rather than silently dropping to a smaller quant. Measured 2026-07-11 · harness 2.0.0-standalone.

NVIDIA GeForce RTX 4090 specifications

ArchitectureAda Lovelace
CUDA cores16,384
VRAM24GB GDDR6X
Memory bus384-bit
Memory bandwidth1008 GB/s
Boost clock2,520 MHz
TDP450 W
Process4nm
InterfacePCIe 4.0 x16
Release date2022-10-12
Launch MSRP$1,599

Verdict, capable, but 24GB sets the ceiling

NVIDIA GeForce RTX 4090 scores 10.4/100, #29 of 102. It ran 8 of 12; 4 exceeded its 24GB. Every figure here is our own measurement.

Relative performance: where the NVIDIA GeForce RTX 4090 lands

100% = this card, AI & Machine Learning headline metric (AI Score). #5 of 61 desktop cards in this vertical.

GPURelative%AI Score
NVIDIA RTX 6000 Ada Generation
229%23.8
NVIDIA GeForce RTX 5090
214%22.3
NVIDIA RTX 5880 Ada Generation
157%16.3
NVIDIA RTX 5000 Ada Generation
106%11
NVIDIA GeForce RTX 4090
100%10.4
NVIDIA GeForce RTX 3090 Ti
82%8.5
NVIDIA Titan RTX
79%8.2
NVIDIA GeForce RTX 3090
74%7.7
AMD Radeon RX 7900 XTX
64%6.7

Same card, other workloads: NVIDIA GeForce RTX 4090 Gaming benchmarks

← All AI & Machine Learning GPU rankings

The silicon

Transistors76,300 million
Die size608.5 mm²
Process node4 nm
Fabricated byTSMC
Transistor density125.4 million per mm²

Denser than 99% of the 76 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.

Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.

What this card can build

Whole-job timings, composed from our measured per-model results on this card.

WorkflowTimeEnergyBasis
24-frame storyboard5 min24.32 Whall 2 stages measured
60-second AI short film7.9 min30.54 Whall 3 stages measured
Full codebase review10.5 min30.47 Whmeasured
10 short social clips22.7 min125.77 Whall 3 stages measured

Can't run: 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs FLUX.1 dev), 20 long-form articles (needs Llama 3.3 70B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).

Rent or buy?

This card is $1,599 to buy. The cheapest listed rate on Vast.ai is $0.155/hour, but that is the floor: we budget $0.186/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 8,597 GPU-hours. Below it you are paying for idle silicon.

How you would use itGPU-hours a yearRental cost a yearTime to break even
2 hours a day, hobby730$13611.8 years
8 hours a day, working on it2,920$5432.9 years
24/7, always-on agent8,760$1,62911.8 months

At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.

Rental price

$0.155/hr+14.0% since 2026-08-14low $0.135 · high $0.155

Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.