ENPT

Jebadiah (27B / 9B v2.1)

Last updated:

Open106–106ms$0/M input

Quadrant scores

See the full quadrant

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

  • Maturity5.8/10

    Apache-2.0 full weights in 27B and 9B (Qwen3.8-27B, Qwen3.5-9B), with GGUF for llama.cpp, Ollama and LM Studio, MLX 4- and 8-bit builds, vLLM support and a browser playground. Code and run-locally docs on GitHub. No hosted API, no SLA.

  • Capability7.1/10

    Decision Index 0.4.1 (22 Oct) Full 64.40 (#25) for the 27B v2.1 (9B: 50.90, #80), above Jev 1.13 (59.22). Choice, noul and score over option labels in one forward pass. No ECE published. Author median 106.5 ms on an RTX PRO 6000.

  • Adoption1/100

    About 280 downloads across the 27B and 9B repos and one like (20 Oct), plus GGUF and MLX mirrors. No production users found.

Vendor claims

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

What it is

Open decision model in 27B and 9B (Apache-2.0) with GGUF, Ollama and MLX builds: choice, noul and score in one pass. Decision Index 0.4 Full 65.37 (#14). Source: github.com/getainode/jebadiah. The card still quotes older board data (27B Full 55.94, 9B 44.91, 15 Oct) for an earlier version; the 0.4 rows are for v2.1 (t1e).

Board result

Board Row Result
Decision Index 0.4 (20 Oct 2026) Jebadiah (27B / 9B v2.1) Full 65.37 (#14); 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)

  • In-process request latency on an RTX PRO 6000: median 106.5 ms for v2.1 (110.2 ms previous) (source)

Scores (from scratch, 20 Oct 2026)

  • Capability 7.1 = types × 0.30 + calibration × 0.25 + latency × 0.25 + accuracy × 0.20 = 10 × 0.30 + 4 × 0.25 + 6 × 0.25 + 8 × 0.20 = 7.10. Accuracy: 8 × 65.37 ÷ 61.26 = 8.54 → 8.
  • Maturity 5.8 = availability × 0.30 + docs × 0.25 + integrations × 0.25 + support × 0.20 = 7 × 0.30 + 7 × 0.25 + 6 × 0.25 + 2 × 0.20 = 5.75 → 5.8.
  • Adoption 1 = engagement × 0.35 + ecosystem × 0.35 + production × 0.30 = 2 × 0.35 + 2 × 0.35 + 0 × 0.30 = 1.40 → 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 64.40 (#25). Accuracy rule: 8 × 64.40 ÷ 59.22 = 8.70 → 8 (was 8). Capability unchanged. Maturity and adoption unchanged.