google/gemma-2-9b-it

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b97-5288-72d6-919b-3df6be2e8a30 · signed

Headline metrics

TTFT P50 (ms)	16.89
TTFT P99 (ms)	—
Throughput (tok/s)	—
$/M tokens	—
J/token	—
Power avg (W)	—
Power peak (W)	—
WER mean	—
J / audio s	—

All metrics

accuracy	1.00
accuracy_p05	1.00
accuracy_p50	1.00
accuracy_p95	1.00
n_ok	10.00
n_samples	10.00
ok_rate	1.00
tokens_out_total	205
total_p50_ms	142
ttft_p50_ms	16.89

Provenance

Model revision	`unknown00`
Provider	vllm
Hardware fingerprint	`550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7`
Dataset	builtin-factual-mini · `e5232bb18b090369b2ecf5029d03a22847760b5f2839779afa65cbfef67ba948`
Timestamp	2026-05-18T14:57:13.352668+00:00
Envelope JSON	81af7eb9aff9.json

Verify this result

bench verify /bench/leaderboard/envelopes/81af7eb9aff9.json

bench verify re-downloads this envelope, recomputes the canonical content hash, and validates the Sigstore signature against the embedded certificate + Rekor entry.