NInfer Qwen3.8-27B NVFP4
Data: JevBench v1.6.1, published 2026-10-06
Capability 68.0 · Not ranked in the current release
cost 7.1× Jev (v1.5 reference)
Last measured: 2026-10-02 · measurement release: v1.6.1
Apache-2.0 (engine and submitted 27B artifact/base)
intelligence
51.8
calibration
84.2
speed
90.5
cost
29.1
Composite (secondary)
17.7 · Composite rank #68
Cost and measurement conditions
$0.231 per 1,000 decisions (estimated)
v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): price floor: base-model reference price applied
Measured p50 latency: 0.055 s (on-GPU, no network, loopback; not directly comparable with API latency, which we time end to end from our measuring host, network included)
Ranking and cap use: 0.26 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.055 s on-GPU, no network (timed on our GPU over loopback). Not directly comparable with API latency, which we time end to end from our measuring host, network included. The ranking and latency cap use the same estimate for every self-hosted row: 2 × measured + 150 ms = 0.26 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
evaluator-owned Lium GPU pod (RTX5090), offline read-only container