RYOTIDE-Gemma (csabag, Gemma-4-E4B stock weights)
Data: JevBench v1.6.39, published 2026-10-22
Capability 55.2 · Not ranked in the current release
unpriced: the frozen pricing path has no market-listing decision for the declared base google/gemma-4-E4B-it and raises rather than estimating; one listing decision would make the row rankable.
Last measured: 2026-10-16 · measurement release: v1.6.26
per base model (stock weights; code licence not checked)
intelligence
36.1
calibration
74.4
speed
89.2
cost
—
Composite (secondary)
— · Not ranked on this board
Cost and measurement conditions
not published (not published)
UNPRICED. The frozen pricing_v15 module (sha256 3948e3f1..., and the later re-freezes, which only add or re-price hosted-API launch-list keys) has no market-listing decision for the declared base google/gemma-4-E4B-it (the module RAISES 'base model lacks an explicit market-listing decision'); no price is invented here. Axes only: Intelligence, Calibration and Speed are computed; Cost, composite and rank are void. Tokens as reported by the author's server (input 2,095,834, output_tokens 0).
Measured p50 latency: 0.095 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: 0.34 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.095 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 = 0.34 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
Evaluator-owned rented Lium GPU pod (measurement receipts on file), 1x NVIDIA H100 80 GB HBM3 (sm_90, driver 580.178.04, United States node, pre-registration Amendments 1-2) - the card most of these systems were first evaluated on, but a different pod, stack and pin set from the earlier runs, so Speed is as measured on this card and probabilities may differ from the earlier runs in the last digits. Python packaging: uv venv from a hashed lock at the old pins, dependencies resolved as of the old build time where the old freeze is lost (declared deviation, UNVERIFIED where noted). Isolation: author server started inside a network namespace with loopback only, the cut proven before and after the sealed input was staged, synthetic smoke gate passed in between; runner unchanged (run_v15.py --resume --resume-keep-failures); one use of input-selfhosted-1500 (custody #20324, under the pre-registration). Published Speed uses the standing x2 + 0.15 s self-hosted adjustment. Author's own server, next-token softmax over the option markers, T 1.924.