Skip to content
runcrate
Console

Benchmarks

GPU benchmarks. From real runs.

Inference, training, images, audio and embeddings, measured on rented GPUs. Every result carries its run date, its method and what it cost.

Launch an H100See GPU prices

Benchmark pages

Benchmarks

Every benchmark page.

LLM inferenceCost per GPU.$0.12 per 1M output tokens. RTX A6000, vLLM, 64 concurrent requests, at the run-day price, run 2026-10-26, single run.A100 vs H100 vs H200One script, six GPUs.718.46 bf16 TFLOPS. H200, dense bf16 matmul at 8192, run 2026-10-25, single run.Speech to textAudio hours per dollar.315x real time. RTX 5090, faster-whisper large-v3-turbo, batch 16, run 2026-10-28, single run.Text embeddingsCost per passage.$0.032 per 1M passages. L40S, bge-small, 128-token passages, at the run-day price, run 2026-10-29, single run.Training and fine-tuningMemory, speed, cost.14.5 GiB peak memory. LoRA of Qwen2.5-1.5B on an L40S, micro-batch 4, run 2026-10-28, single run.Image generationImages per dollar.$0.91 per 1,000 images. RTX A6000, compiled, batch 1, at the run-day price, run 2026-10-27, single run.GPU startup timeTimed from the API call.186 s to the first CUDA op. L40S, from the create call to a 4096 x 4096 matmul, run 2026-10-26, single run.

Runs

Every run. Newest first.

BenchmarkGPUsRun date
BGE embedding throughput per dollarRTX 5090, L40S, RTX A6000, H1002026-10-29
torch.compile vs eager for trainingRTX 5090, L40S, RTX A6000, H1002026-10-29
Hugging Face download vs local cacheL40S2026-10-29
Ollama Q4 vs vLLM bf16 on a 24 GB A10A102026-10-28
Whisper large-v3 audio hours per dollarRTX 5090, L40S, RTX A6000, H1002026-10-28
Full fine-tune vs LoRA vs QLoRA on one L40SL40S2026-10-28
FP8 vs bf16 on an H100H1002026-10-27
Prefix caching on vs offL40S2026-10-27
SDXL images per dollar on four GPUsRTX A6000, L40S, RTX 5090, H1002026-10-27
Qwen2.5-7B on vLLM, three GPUsRTX A6000, L40S, H1002026-10-26
PyTorch DDP on four PCIe RTX A6000sRTX A60002026-10-26
Launch to first CUDA matmulL40S, A100 80GB, RTX A4000, RTX 6000 Ada, RTX A60002026-10-26
One script on six GPUsH200, H100, A100 80GB, L40S, RTX A6000, RTX A40002026-10-25

Costs

How the costs are worked out. Run day and today, side by side.

Run day

The cost the write-up printed: the hourly price the machine was launched at that day, against what it measured. Prices move daily, so each run-day figure carries its date. Every run was a single run.

Today

The run-day figure moved by today's price: the "from" price per GPU-hour shown on /pricing, over the run-day rate per GPU-hour. A GPU that is not in stock right now reads "Not in stock" rather than a stale price. Prices read 2026-11-04 04:00 UTC.