ENPT

mogan-decision-31B-it

Last updated:

Open107–107ms$0/M input

Quadrant scores

See the full quadrant

Scored with the public quadrant rubric (maturity × capability; bubble = adoption). Revise as evidence lands.

  • Maturity3.9/10

    LoRA (r 128) on google/gemma-4-31B-it, merged into bf16 at inference, under CC-BY-NC-4.0 (non-commercial). Card with engine class, temperatures and published Decision Index results. No hosted API, no integrations, no SLA.

  • Capability5.9/10

    Decision Index 0.4.1 (22 Oct) Full 59.82 (#44), level with Jev 1.13 (59.22). Choice (2–255 options) and yes/no only, temperature fitted per option count, no ECE. Author median 107 ms in-process.

  • Adoption1/100

    About 59 downloads and one like (20 Oct). No integrations or production users found.

Vendor claims

publicado (OK do Fabricio 20/10 BRT). Scores are calculated from scratch.

What it is

MoganAI’s non-commercial LoRA for Gemma 4 31B: choice and yes/no with a probability per option, no generated text. Decision Index 0.4 Full 61.06 (#35). Source: huggingface.co/moganai/mogan-decision-31B-it. The card still reports Decision Index editions 0.2 and 0.2.1; the 0.4 Full is the board’s own run.

Board result

Board Row Result
Decision Index 0.4 (20 Oct 2026) mogan-decision-31B-it Full 61.06 (#35); Jev 1.13 61.26 (#34), Jev 1.14 62.22 (#28)

Not checked against JevBench or Artificial Analysis for this page; the boards are never combined.

Vendor claims (UnverifiedClaim)

  • Self-run Decision Index: 65.42 on edition 0.2.1 and 60.17 on 0.2 (151,476 requests, official kit), self-reported until maintainers reproduce (source)
  • Median in-process latency 107 ms per request (source)

Scores (from scratch, 20 Oct 2026)

  • Capability 5.9 = types × 0.30 + calibration × 0.25 + latency × 0.25 + accuracy × 0.20 = 6 × 0.30 + 4 × 0.25 + 6 × 0.25 + 8 × 0.20 = 5.90. Accuracy: 8 × 61.06 ÷ 61.26 = 7.97 → 8.
  • Maturity 3.9 = availability × 0.30 + docs × 0.25 + integrations × 0.25 + support × 0.20 = 5 × 0.30 + 6 × 0.25 + 2 × 0.25 + 2 × 0.20 = 3.90.
  • Adoption 1 = engagement × 0.35 + ecosystem × 0.35 + production × 0.30 = 1 × 0.35 + 1 × 0.35 + 0 × 0.30 = 0.70 → 1.

Board audit (22 Oct 2026, DI 0.4.1)

publicado (OK do Fabricio 22/10 BRT).

Decision Index 0.4.1 (22 Oct; reference Jev 1.13 Full 59.22, was 61.26 on 0.4) lists this page’s row at Full 59.82 (#44). Accuracy rule: 8 × 59.82 ÷ 59.22 = 8.08 → 8 (was 8). Capability unchanged. Maturity and adoption unchanged.