Live marketplace snapshot
Observed (UTC): 2026-11-18T14:11:56+00:00Snapshot SHA-256: a80cc0e6d59b…Freshness guard: auto-grays after 72h
Terminal speed-math — no install needed
Size any model from a real terminal, straight off this page's live snapshot:
curl -fsSL https://gpuvram.pages.dev/vram-cli.py | python3 - qwen3-8-27b --ctx 32768
Full live GPU rate table — RunPod vs Vast.ai
| GPU | VRAM (GB) | RunPod Secure ($/hr) | RunPod Community ($/hr) | Vast.ai Verified ($/hr) | Lowest ($/hr) | Deploy |
|---|---|---|---|---|---|---|
| B300 288GB | 288 | $8.99 | $6.94 | — | $6.94 | RunPodVast |
| MI300X 192GB | 192 | $2.39 | $0.50 | — | $0.50 | RunPodVast |
| B200 180GB | 180 | $7.99 | $5.98 | — | $5.98 | RunPodVast |
| H200 NVL 143GB | 143 | $3.79 | $0.50 | — | $0.50 | RunPodVast |
| H200 140GB | 141 | $5.29 | $3.59 | — | $3.59 | RunPodVast |
| H100 NVL 94GB | 94 | $3.19 | $2.59 | — | $2.59 | RunPodVast |
| A100 PCIe 80GB | 80 | $2.09 | $1.19 | $0.87 | $0.87 | VastRunPod |
| A100 SXM 80GB | 80 | $2.19 | $1.39 | $0.52 | $0.52 | VastRunPod |
| H100 PCIe 80GB | 80 | $2.89 | $1.99 | — | $1.99 | RunPodVast |
| H100 SXM 80GB | 80 | $4.39 | $2.69 | $2.27 | $2.27 | VastRunPod |
| A40 48GB | 48 | $0.59 | $0.35 | $0.47 | $0.35 | RunPodVast |
| L40 48GB | 48 | $0.82 | $0.69 | $0.46 | $0.46 | VastRunPod |
| L40S 48GB | 48 | $1.09 | $0.79 | $0.77 | $0.77 | VastRunPod |
| RTX 6000 Ada 48GB | 48 | $1.09 | $0.74 | $0.52 | $0.52 | VastRunPod |
| RTX A6000 48GB | 48 | $0.69 | $0.33 | $0.40 | $0.33 | RunPodVast |
| A100 SXM 40GB | 40 | — | $1.00 | — | $1.00 | RunPodVast |
| RTX 5090 32GB | 32 | $1.39 | $0.69 | $0.44 | $0.44 | VastRunPod |
| RTX 3090 24GB | 24 | $0.50 | $0.22 | $0.27 | $0.22 | RunPodVast |
| RTX 4090 24GB | 24 | $0.89 | $0.34 | $0.39 | $0.34 | RunPodVast |
| RTX A5000 24GB | 24 | $0.27 | $0.16 | — | $0.16 | RunPodVast |
| RTX A4000 16GB | 16 | $0.25 | $0.17 | $0.09 | $0.09 | VastRunPod |
— means no live on-demand stock from that channel at snapshot time. Vast rates are the lowest verified, rentable single-GPU on-demand bundle.
What standing still costs you
Run one H100 SXM 80GB around the clock (730 h/month): RunPod Secure bills $3204.70/mo, while the cheapest verified Vast.ai bundle bills $1656.30/mo — a real gap of $1548.40 every single month, or $18580.84 per year, for the identical GPU class.
By comparison, the hyperscalers' list rates for on-demand A100/H100-class instances (AWS p4d/p5, GCP A3) commonly land in the several-dollars-per-GPU-hour range with rigid 1-year terms — before egress fees. The community/verified spot channels above rent the same silicon by the hour with zero commitment. Check the live table before any monthly commitment; the gap is real and measurable.
FAQ
How is the KV cache computed? With grouped-query attention, only the KV heads carry cache: 2 (K and V) × hidden layers × kv heads × head_dim × context × sequences. We read layer/head counts straight from each repo's config.json on Hugging Face.
Why 16-bit weights for some models and not others? The calculator lets you pick FP16, FP8, or 4-bit; parameter counts come from the actual safetensors totals, so a 4-bit quant of a 32B model is sized from its true 32B params, not a marketing number.
Are these prices really live? Yes. Every rate in the table was returned by RunPod's GraphQL endpoint or Vast.ai's verified on-demand bundle API at the snapshot timestamp above, and the SHA-256 fingerprint of the raw response file is published so you can audit us.