Benchmarks
Real performance data, not marketing claims. Our benchmarks test every GPU we offer across LLM inference, image generation, OCR, and TTS workloads on dedicated GPU servers. See our tokens/sec benchmark for the latest results.
Flux.1 on RTX 3090: Images/sec & VRAM Usage, Category: Benchmarks, Slug: flux-1-on-rtx-3090-benchmark, Excerpt: Flux.1 benchmarked on RTX 3090: 0.82 it/s, 2.46 images/min at 1024×1024, VRAM usage, and cost per 1K images., Internal links: 8 –>
Flux.1 benchmarked on RTX 3090: 0.82 it/s, 2.46 images/min at 1024x1024, VRAM usage, and cost per 1K images., Internal links: 8 -->
Flux.1 on RTX 5080: Images/sec & VRAM Usage, Category: Benchmarks, Slug: flux-1-on-rtx-5080-benchmark, Excerpt: Flux.1 benchmarked on RTX 5080: 1.25 it/s, 3.75 images/min at 1024×1024, VRAM usage, and cost per 1K images., Internal links: 8 –>
Flux.1 benchmarked on RTX 5080: 1.25 it/s, 3.75 images/min at 1024x1024, VRAM usage, and cost per 1K images., Internal links:…
Flux.1 on RTX 5090: Images/sec & VRAM Usage, Category: Benchmarks, Slug: flux-1-on-rtx-5090-benchmark, Excerpt: Flux.1 benchmarked on RTX 5090: 1.85 it/s, 5.55 images/min at 1024×1024, VRAM usage, and cost per 1K images., Internal links: 8 –>
Flux.1 benchmarked on RTX 5090: 1.85 it/s, 5.55 images/min at 1024x1024, VRAM usage, and cost per 1K images., Internal links:…
SD 1.5 on RTX 3050: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-3050-benchmark, Excerpt: SD 1.5 benchmarked on RTX 3050: 2.8 it/s, 6.72 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 3050: 2.8 it/s, 6.72 images/min at 512x512, VRAM usage, and cost per 1K images., Internal…
SD 1.5 on RTX 4060: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-4060-benchmark, Excerpt: SD 1.5 benchmarked on RTX 4060: 6.2 it/s, 14.88 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 4060: 6.2 it/s, 14.88 images/min at 512x512, VRAM usage, and cost per 1K images., Internal…
SD 1.5 on RTX 4060 Ti: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-4060-ti-benchmark, Excerpt: SD 1.5 benchmarked on RTX 4060 Ti: 8.4 it/s, 20.16 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 4060 Ti: 8.4 it/s, 20.16 images/min at 512x512, VRAM usage, and cost per 1K images.,…
SD 1.5 on RTX 3090: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-3090-benchmark, Excerpt: SD 1.5 benchmarked on RTX 3090: 12.5 it/s, 30.0 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 3090: 12.5 it/s, 30.0 images/min at 512x512, VRAM usage, and cost per 1K images., Internal…
SD 1.5 on RTX 5080: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-5080-benchmark, Excerpt: SD 1.5 benchmarked on RTX 5080: 18.2 it/s, 43.68 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 5080: 18.2 it/s, 43.68 images/min at 512x512, VRAM usage, and cost per 1K images., Internal…
SD 1.5 on RTX 5090: Images/sec & VRAM Usage, Category: Benchmarks, Slug: sd-1.5-on-rtx-5090-benchmark, Excerpt: SD 1.5 benchmarked on RTX 5090: 25.5 it/s, 61.2 images/min at 512×512, VRAM usage, and cost per 1K images., Internal links: 8 –>
SD 1.5 benchmarked on RTX 5090: 25.5 it/s, 61.2 images/min at 512x512, VRAM usage, and cost per 1K images., Internal…
Whisper Large-v3 on RTX 3050: Transcription Speed & Cost, Category: Benchmarks, Slug: whisper-large-v3-on-rtx-3050-benchmark, Excerpt: Whisper Large-v3 benchmarked on RTX 3050: RTF 0.28, 3.6x real-time processing, VRAM usage, and cost per audio hour., Internal links: 8 –>
Whisper Large-v3 benchmarked on RTX 3050: RTF 0.28, 3.6x real-time processing, VRAM usage, and cost per audio hour., Internal links:…
Explore GPU Hosting Solutions
From the blog to your next deployment — pick the right platform for your workload.
Tokens/sec Benchmarks
Real-world tokens per second data across every GPU we offer, tested on popular LLMs.
View BenchmarksTTS Latency Benchmarks
Time-to-first-audio for Coqui, Bark, Kokoro, and XTTS-v2 across GPU tiers.
View TTS BenchmarksOCR Speed Benchmarks
Pages per second for PaddleOCR and Tesseract across our GPU server lineup.
View OCR BenchmarksCost per 1M Tokens
What does it cost to process a million tokens on each GPU? Interactive calculator.
Calculate CostDedicated GPU Hosting
Bare-metal servers with a dedicated GPU, NVMe, full root access, and 1Gbps networking from our UK datacenter.
Browse GPU ServersOpen Source LLM Hosting
Deploy LLaMA, Mistral, DeepSeek, and more on dedicated hardware with no per-token API fees.
Explore LLM HostingReady to deploy your AI workload?
Dedicated GPU servers from our UK datacenter. NVMe storage, 1Gbps networking, full root access.
65 Victory Avenue
PE7 1XU, England
GPUAIR © All Rights Reserved.