Model cards

These are the models available through decision-toolkit. Each card explains how to load and use the model, its variants, the measured evidence and its known limitations.

Model	Adapter	Variants (default *)	Pinned	Latency (CPU)	Evidence
GLiNER2.5 multi	gliner2	fp16* · 577 MB; fp32 · 1132 MB	3de2c11f	353 ms	9/15 routing; same as local int8
GLiNER2.5-Decide	gliner2-decide	q4f16* · 524 MB	18271032	912 ms	refund 0.944 (card example)
Laya (English)	laya	q8* · 528 MB	cccc9a01	514 ms	torch parity: Δp ≤ 0.005
Julia 1	julia	fp32* · 618 MB	82a2fadf	329 ms	100/100 argmax; 8.5e-05 max logit error
OpenDecider nano	opendecider	q8f16* · 469 MB; fp16 · 792 MB	5137ae7b	530 ms	official build; prompt ported from pinned code
Laya multilingual	laya	fp16* · 682 MB; fp32 · 1326 MB	46b77bbf	37 ms	fused ONNX; upstream Δp ≤ 0.035
Open-Jev DeBERTa v3 large	open-jev	fp16* · 884 MB; fp32 · 1758 MB; q4 · 487 MB; q4f16 · 357 MB	7c79f25b	241 ms	0.854 in-domain; 0.690 OOD (upstream)
Strands Decider 2B	strands-decider	q4f16* · 1114 MB; q8 · 1821 MB	31a83e02	719 ms	reference fixture max Δp 0.018

A * marks the default. To inspect sizes, hashes and exact commands, run dtk models variants <id> or read Variants and quantization. For cache locations, offline installs and model selection, see Models and the model cache.

Latencies above are CPU measurements. Reproducible post-warmup measurements and the exact command are in BENCH.md.