deck-4B v1.0 (krishna765, JevK5 + LoRA, FP8 weight-only)
Data: JevBench v1.6.1, published 2026-10-06
Capability 63.6 · rank #13 of 64
Last measured: 2026-10-05 · measurement release: v1.6.1
Licence not stated
intelligence
38.6
calibration
88.6
speed
89.9
cost
63.5
Composite (secondary)
37.3 · Composite rank #20
Cost and measurement conditions
$0.017 per 1,000 decisions (estimated)
ESTIMATE (v1.5-M2 base-model reference; self-hosted open weights, no public tariff): DeepInfra Qwen/Qwen3.5-4B list price $0.03/M input, $0.15/M output (base of JevK5, the adapter's base checkpoint; not on OpenRouter; frozen 25 Sep snapshot per I-3, same reference as reflex-4b, jobe, typecastlm and Quyet) x the server's own measured usage.input_tokens; logit readout, 0 output tokens; FP8 weight-only on 1x RTX PRO 6000 96GB (Lium; v1.6 GPU-class deviation from source H100), deck-4b 1.0.0 + jevk5 f944fe37; estimated, not charged
p50 latency: 0.3 s
x2 + 0.15 s (assumption, not measured)
Setup not stated