whatmodel.sh / decision / Jebadiah 9B v2.1 (Ollaya Q8_0)

Jebadiah 9B v2.1 (Ollaya Q8_0)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Jebadiah 9B v2.1 (Ollaya Q8_0) is an open-weights decision model from frontier-infra, released October 2026. Licence: apache-2.0.

Catalogue identity notes

Ollaya native AINode prompt and per-type temperatures, one pass, Q8_0. This is not the repeated-payload/forward-reverse T1e recipe; its scores stay separate. Source GGUF jebadiah-9b-v2-1-Q8_0.gguf at 2182dd8d70b09ffdce5b68b0ddf6c4591bf38810; weight sha256:031de099ea132414cbcb89ac363d44fe5ff09c71994028825ce671a4e1bd51f1; Ollaya manifest 737d66d5ad2aaf17e4271257a8b7853a6613967d6953bda3c8167fb8e6d5270c. Published training-overlap subsets are excluded. Local memory is the measured RTX 5090 peak increase during the short five-question triage workload (9315 MiB), rounded upward to 0.1 GiB; longer contexts can require more. Command verified from upstream documentation, not freshly executed here.

Model information sources

Release date ↗ · Weights licence ↗

55.2±3.4#158 of 355 decision modelsfrom 9 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Jebadiah 9B v2.1 (Ollaya Q8_0), out of 357 with a score, then more from frontier-infra.

#modelscorewhereRAMreleased
158StartLux-Decision v1.1 2B StartLux55±1model files
159kev-4b (DecisionBench 485ace87) Jared Palmer55±2model files
160Jebadiah 9B v2.1 (Ollaya Q8_0) frontier-infra55±3local~9.1GB2026-10
161Standard One 8B SH (v4) Standard Thinking55±1model files
162kev-8b (DecisionBench c80773da) Jared Palmer55±2model files
more from frontier-infra
57Jebadiah 27B v2.1 (T1e) frontier-infra65±1local~69GB2026-10
125Jebadiah 27B v2.1 (Ollaya Q4_K_M) frontier-infra59±4local~16GB2026-10
143Jebadiah 9B v2.1 (T1e) frontier-infra57±1local~25GB2026-10

see all decision models · find the ones that fit your machine

$ what it's good at

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #137 of 263 · 45% of its score · 5 tests

Beats Winnow-12B (DecisionBench b6ac22b0), Amber Hybrid 4B (decision readout), StartLux-Decision v1.1 2B here, though they rank higher overall. Trails mmastrac diffgemma (decision readout), djev diffgemma (decision readout), Kev 9B v2 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Ollaya · PubMedQA76.0% ✎▃▂▃▃·▂▃▃▆█▆▂ beats 22/25easy · avg 69%▇▇▇▇▇▇ 16%at its level
Ollaya · BoolQ87.0% ✎▁··▃▃▁▄▁▃█▇▄ beats 19/25easy · avg 84%▇▇▇▇▇ 12%typical
Ollaya · SQuAD 2 answerability85.6% ✎▁▁▃▁▇█▃▃▄▃·▁ beats 20/25easy · avg 80%▇▇▇ 6.5%blunt
Ollaya · VitaminC verification75.8% ✎▁···▃·▄█▃··▁ beats 9/25easy · avg 78%▇▇ 6.2%blunt
Ollaya · MultiNLI83.3% ✎▂··▄██▂▆▆█▆▂ beats 10/25very easy · avg 87%▇▇ 3.9%blunt
workflows▁▁▁▂▁▂▂▆█▄▁▁ #46 of 114 · 50% of its score · 4 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Ollaya · SummEval relevance49.2% ✎▁··▁▂▁▅··▃██ beats 19/25medium · avg 41%▇▇▇▇▇▇ 15%at its level
Ollaya · PAWS paraphrase85.2% ✎▂▂▂▂·▃█▆·▂·▁ beats 22/25easy · avg 81%▇▇▇▇▇▇ 15%typical
Ollaya · Aegis 2 safety78.8% ✎▂·▁▁▂·▃▃▃█▃▁ beats 12/25easy · avg 77%▇▇▇▇▇ 13%typical
Ollaya · SummEval consistency85.4% ✎▁·▁▁··▁▁▁▁▄█ beats 24/25easy · avg 75%▇▇▇ 6.9%sharp · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs 9.1 GB, NVIDIA only · from github.com/ollaya-dev
    ollaya run jeb:9b --preset triage "The customer requests a refund."

Download model files ↗
Public ungated original GGUF verified at the exact benchmark manifest revision. Install the Ollaya runtime separately using its official installation instructions. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/frontier-infra ↗

$ how the score was worked out · Ollaya · original runs 95%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Ollaya · original runs9Apache-2.0
prior · pull toward the middle
weighted average= 55.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json