NVIDIA A800 80GB, AI & Machine Learning Benchmarks & Specs

80GB · AI Score 33.1/100 · anchored estimate vs 51 measured cards

33.1 AI Score Includes estimates

We have not run NVIDIA A800 80GB on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: high (sibling silicon)). On Llama 3.1 8B (Q4_K_M) NVIDIA A800 80GB should deliver about 162.6 tokens/sec. Stepping up to Qwen3 32B it should hold roughly 45.5 tok/s. The full Llama 3.3 70B still runs, at about 24.4 tok/s. For image generation, SDXL should run near 8.18 it/s, and FLUX.1-dev at 1.99 it/s. All 12 workloads fit in 80GB. There is no model in our suite this card has to turn down.

AI & Machine Learning benchmark results

Text Generation tok/s 5

Qwen3 4B197
Llama 3.1 8B162.6
Qwen2.5-Coder 14B89.5
Qwen3 32B45.5
Llama 3.3 70B24.4
WorkloadResultTelemetryData
Qwen3 4B197 tok/sestimatedEst.
Llama 3.1 8B162.6 tok/sestimatedEst.
Qwen2.5-Coder 14B89.5 tok/sestimatedEst.
Qwen3 32B45.5 tok/sestimatedEst.
Llama 3.3 70B24.4 tok/sestimatedEst.

Image Generation images/min 3

Stable Diffusion XL16.36
Z-Image Turbo9.975
FLUX.1 dev4.264
WorkloadResultTelemetryData
Stable Diffusion XL16.36 images/minestimatedEst.
Z-Image Turbo9.98 images/minestimatedEst.
FLUX.1 dev4.26 images/minestimatedEst.

Image Editing images/min 2

WorkloadResultTelemetryData
FLUX.1 Kontext dev1.99 images/minestimatedEst.
Qwen-Image-Edit1.64 images/minestimatedEst.

Video Generation frames/s 2

WorkloadResultTelemetryData
LTX-Video (distilled)8.95 frames/sestimatedEst.
Wan 2.2 5B (720p)0.66 frames/sestimatedEst.
How this estimate is derived. This card hasn’t been through our bench yet, so its numbers are anchored estimates, interpolated from the 51 first-party measured cards (Sibling to measured A100 80GB SXM: identical compute+bandwidth (export SKU, NVLink cut to 400GB/s, no single-GPU impact)). The VRAM “won’t fit” gates are exact, since they’re pure capacity limits. Confidence: high (sibling silicon). Estimates are replaced with measured data as more silicon goes through the bench. Full methodology →

NVIDIA A800 80GB specifications

ArchitectureAmpere
CUDA cores6,912
VRAM80GB HBM2e
Memory bus5120-bit
Memory bandwidth2039 GB/s
Boost clock1,410 MHz
TDP400 W
ProcessTSMC 7nm
InterfaceSXM4
Release date2022-11-01
Launch MSRP$15,000

Verdict, NVIDIA A800 80GB on real AI workloads

NVIDIA A800 80GB scores 33.1/100, #14 of 102. It ran all 12 workloads. Figures are anchored estimates, not measurements, we flag that on every row.

Relative performance: where the NVIDIA A800 80GB lands

100% = this card, AI & Machine Learning headline metric (AI Score). #12 of 21 desktop cards in this vertical.

GPURelative%AI Score
NVIDIA H800 80GB
189%62.6
NVIDIA RTX PRO 6000 Blackwell Server Edition
151%49.9
NVIDIA H100 PCIe
140%46.4
NVIDIA A100 80GB SXM4
100%33.1
NVIDIA A800 80GB
100%33.1
NVIDIA A100 80GB PCIe
96%31.7
NVIDIA L40S
84%27.7
NVIDIA L40
59%19.5
NVIDIA A40
53%17.7

← All AI & Machine Learning GPU rankings

What this card can build

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

WorkflowTimeEnergyBasis
24-frame storyboard2.9 minn/aestimate, 0 of 2 stages measured
60-second AI short film4 minn/aestimate, 0 of 3 stages measured
6-panel comic page4.7 minn/aestimate, 0 of 3 stages measured
Character sheet, 12 poses6.3 minn/aestimate, 0 of 2 stages measured
Full codebase review11.2 minn/aestimate, 0 of 1 stage measured
10 short social clips13.6 minn/aestimate, 0 of 3 stages measured
20 long-form articles19.1 minn/aestimate, 0 of 1 stage measured
40-product photo shoot22.5 minn/aestimate, 0 of 2 stages measured
100-photo restoration batch50.2 minn/aestimate, 0 of 1 stage measured