HEAD TO HEAD
Andy Zhang: ajev and Fastino Labs: gliner2-5-decide, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | fastino-labs/gliner2-5-decide |
|---|---|---|
| Summary | An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass. | 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, score, noul | choice, score, noul, classify, extract, route |
| Architecture | ajev | gliner2 |
| Fine-tuned from | google/gemma-4-26b-a4b-it | fastino/gliner2-large-v1 |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Fastino |
| Input price | — | — |
| Decision accuracy | — | 60.2% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 49 ms | 38.3 ms |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | Fastino fast-decisions suite (17 datasets) |
| Latest version | 2026.09 | 2026.09.25 |
| Variants | — | encoder_config |
| Size of latest version | 141.9 MB | 1.8 GB |
| Files | 3 | 6 |
| Downloads | 0 | 75 |
| Stars | 0 | 0 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, encoder, deberta, extraction, gliner, 340m |
| Updated | Oct 7, 2026 | Nov 22, 2026 |
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.
ajev is from Andy Zhang and gliner2-5-decide from Fastino Labs. ajev has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, score and noul questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 26B.
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); ajev does not, so there is no comparison to make without your own test.
ajev: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, gliner2-5-decide answers in about 38.3 ms at the median and ajev in about 49 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull andy-zhang/ajev and systemone pull fastino-labs/gliner2-5-decide download the weights.