InferenceBench

google/gemma-2-9b-it

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b97-72de-7e14-8576-f4e6f36c6c70 · signed

Headline metrics

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

All metrics

n_ok 0.0000
n_samples 5.00
ok_rate 0.0000

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetpersona-consistency-mini · ac864a018c1eb985c7f697a997162da20039e99fff11927ec3139fa4f2d4e9e3
Timestamp2026-05-18T14:57:21.631007+00:00
Envelope JSONef9f4b42b9c2.json

Verify this result

bench verify /bench/leaderboard/envelopes/ef9f4b42b9c2.json

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