GeForce RTX 4080 Super, AI & Machine Learning Benchmarks & Specs

16GB · AI Score 5.4/100 · first-party measured on 12 AI workloads

5.4 AI Score ✓ Measured

Every number on this page is first-party: GeForce RTX 4080 Super 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) GeForce RTX 4080 Super delivers about 126.29 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 16GB. For image generation, SDXL runs at 4.56 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 6 of the 12 workloads won't fit on 16GB at the tested precision, Qwen3 32B, Llama 3.3 70B, FLUX.1-dev, FLUX.1 Kontext and others. We publish those as hard gates rather than quietly dropping to a smaller quant.

Bench notes: from the person who ran it

Being straight with you: two of my runs on this card (Z-Image and LTX video) came back 2-3x slower than the plain 4080 with every LLM number identical. That's a borderline-VRAM offload problem, not the card. Those runs are flagged and excluded from the score until I re-run them. What's solid: 1.72 tokens/watt and it only used 88% of its power rating. 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 4B197.53
Llama 3.1 8B126.29
Qwen2.5-Coder 14B70.55
WorkloadResultTelemetryData
Qwen3 4B197.53 tok/s
2.7 GB peak115 W45°C1.72 tok/WQ4_K_M
✓ Measured
Llama 3.1 8B126.29 tok/s
4.7 GB peak130 W48°C0.98 tok/WQ4_K_M
✓ Measured
Qwen2.5-Coder 14B70.55 tok/s
8.7 GB peak140 W51°C0.51 tok/WQ4_K_M
✓ Measured
Qwen3 32B✕ Won't fit needs ~23 GBVRAM-gated at this precision✓ Measured
Llama 3.3 70B✕ Won't fit needs ~46 GBVRAM-gated at this precision✓ Measured

Image Generation images/min 3

WorkloadResultTelemetryData
Stable Diffusion XL9.12 images/min
14.7 GB peak252 W55°C6.6 s/img
✓ Measured
Z-Image Turbo0.75 images/min
14.1 GB peak74 W57°C77.6 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)1.42 frames/s
9.3 GB peak102 W58°C68.1 s/clip
✓ Measured
Wan 2.2 5B (720p)✕ Won't fit needs ~18 GBVRAM-gated at this precision✓ 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.

GeForce RTX 4080 Super specifications

ArchitectureAda Lovelace
CUDA cores10,240
VRAM16GB GDDR6X
Memory bus256-bit
Memory bandwidth736 GB/s
Boost clock2,505 MHz
TDP320 W
Process4nm
InterfacePCIe 4.0 x16
Release date2024-01-31
Launch MSRP$999

Verdict, capable, but 16GB sets the ceiling

GeForce RTX 4080 Super scores 5.4/100, #44 of 102. It ran 6 of 12; 6 exceeded its 16GB. Every figure here is our own measurement.

Relative performance: where the GeForce RTX 4080 Super lands

100% = this card, AI & Machine Learning headline metric (AI Score). #11 of 61 desktop cards in this vertical.

GPURelative%AI Score
NVIDIA Titan RTX
152%8.2
NVIDIA GeForce RTX 3090
143%7.7
AMD Radeon RX 7900 XTX
124%6.7
AMD Radeon RX 7900 XT
115%6.2
GeForce RTX 4080 Super
100%5.4
GeForce RTX 5080
91%4.9
NVIDIA GeForce RTX 4080
87%4.7
GeForce RTX 5070 Ti
87%4.7
NVIDIA RTX 4000 (Ada Generation)
81%4.4

Same card, other workloads: GeForce RTX 4080 Super Gaming benchmarks

← All AI & Machine Learning GPU rankings

The silicon

Transistors45,900 million
Die size378.6 mm²
Process node4 nm
Fabricated byTSMC
Transistor density121.2 million per mm²

Denser than 87% 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
Full codebase review14.2 min33.05 Whmeasured

Can't run: 60-second AI short film (needs Qwen3 32B), 60-second AI short film, narrated (needs Qwen3 32B), 10 short social clips (needs Qwen3 32B), 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs Qwen3 32B), 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), 24-frame storyboard (needs Qwen3 32B), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).

Rent or buy?

This card is $999 to buy. The cheapest listed rate on RunPod is $0.280/hour, but that is the floor: we budget $0.336/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 2,973 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$2454.1 years
8 hours a day, working on it2,920$9811.0 years
24/7, always-on agent8,760$2,9434.1 months

At steady usage this card pays for itself inside a normal ownership window. 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

$0.280/hr+0.0% since 2026-08-14low $0.280 · high $0.280

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