An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.
Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
Decides
choice, noul, score, classify, route
choice, score, noul, classify, extract, route
Architecture
nimble
gliner2
Fine-tuned from
qwen/qwen3.5-9b
fastino/gliner2-large-v1
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights + hosted API
Hosted by
Bespoke Labs
Fastino
Input price
—
—
Decision accuracy
90.1%
60.2%
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
38.3 ms
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bespoke-nimble-9b and gliner2-5-decide?
bespoke-nimble-9b is from Bespoke Labs and gliner2-5-decide from Fastino Labs. Both have open weights and a hosted API. Both answer choice, noul, score, classify and route questions. Only gliner2-5-decide answers extract. gliner2-5-decide is the smaller model, at 340M parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or gliner2-5-decide?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bespoke-nimble-9b or gliner2-5-decide?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or gliner2-5-decide?
By their publishers’ figures, gliner2-5-decide answers in about 38.3 ms at the median and bespoke-nimble-9b in about 106 ms — measured on different hardware, so treat it as a rough guide.
Can I run bespoke-nimble-9b or gliner2-5-decide locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull fastino-labs/gliner2-5-decide download the weights.
