whatmodel.sh / decision / Jebadiah 4B v2 (Ollaya Q8_0)

Jebadiah 4B v2 (Ollaya Q8_0)

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

Jebadiah 4B v2 (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-4b-v2-Q8_0.gguf at 7f671f9a31827257c26401000484e154b39417e6; weight sha256:36f4a54fe07ed79b186a2128bfb1598ba210b1ab0a945296069a4e5cdbb9875a; Ollaya manifest 4aba27707f6f4ba6f116710a0d05743220e5a5819b8826a9bd32385d0d9df2ff. Published training-overlap subsets are excluded. Local memory is the measured RTX 5090 peak increase during the short five-question triage workload (5530 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 ↗

51.8±3.0#190 of 355 decision modelsfrom 13 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Jebadiah 4B v2 (Ollaya Q8_0), out of 357 with a score, then more from frontier-infra.

#modelscorewhereRAMreleased
190baselabs joey-1 (2B) baselabs52±1api price unknown
191QEV-2B ken-jo52±4model files
192Jebadiah 4B v2 (Ollaya Q8_0) frontier-infra52±3local~5.5GB2026-10
193JEV-9B AutoTrust AI Lab52±1model files
194Aplomb 1 EmpirioLabs AI52±1request access
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▁▂▂▂▂▃▃▅▅▆█▂ #164 of 263 · 36% of its score · 5 tests

Beats StartLux-Decision v1.1 2B, Solomon v1.1, Standard One 3B SH (v4) here, though they rank higher overall. Trails Jobe Qwen3.5-4B (decision readout), SemIf Qwen3.5-4B Base (decision readout), Saracura PT-BR 4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Ollaya · PubMedQA68.8% ✎▃▂▃▃·▂▃▃▆█▆▂ beats 12/25easy · avg 69%▇▇▇▇▇ 13%at its level
Ollaya · BoolQ85.0% ✎▁··▃▃▁▄▁▃█▇▄ beats 12/25easy · avg 84%▇▇▇▇ 10%typical
Ollaya · SQuAD 2 answerability76.3% ✎▁▁▃▁▇█▃▃▄▃·▁ beats 11/25easy · avg 80%▇▇ 5.1%blunt
Ollaya · VitaminC verification76.0% ✎▁···▃·▄█▃··▁ beats 10/25easy · avg 78%▇▇ 4.9%blunt
Ollaya · MultiNLI87.6% ✎▂··▄██▂▆▆█▆▂ beats 14/25very easy · avg 87%▇ 3.1%blunt
workflows▁▁▁▂▁▂▂▆█▄▁▁ #63 of 114 · 60% of its score · 8 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails InternLM Intern-Decision Qwen3.5-4B, StartLux-Decision v1.1 0.8B, JevK5 v0.3 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Ollaya · PAWS paraphrase83.2% ✎▂▂▂▂·▃█▆·▂·▁ beats 18/25easy · avg 81%▇▇▇▇▇ 12%typical
Ollaya · SummEval relevance51.2% ✎▁··▁▂▁▅··▃██ beats 22/25medium · avg 41%▇▇▇▇▇ 11%at its level
Ollaya · MASSIVE German intent83.1% ✎▁····▁·▂▃▆█▃ beats 13/23easy · avg 84%▇▇▇▇ 10%sharp
Ollaya · Aegis 2 safety79.2% ✎▂·▁▁▂·▃▃▂█▃▁ beats 14/25easy · avg 77%▇▇▇▇ 10%typical
Ollaya · SummEval consistency84.0% ✎▁·▁▁··▁▁▁▁▄█ beats 21/25easy · avg 75%▇▇ 6.0%sharp · noisy
Ollaya · MASSIVE English intent85.7% ✎▁·······▂▃█▃ beats 14/23very easy · avg 86%▇▇ 5.3%noisy
Ollaya · HelpSteer 2 scoring39.4% ✎▁▁··▁·▁▃▇█▅▄ beats 16/23medium · avg 38%▇▇ 4.1%blunt · at its level
Ollaya · Civil Comments87.0% ✎▂▂▂·▂▅▅▆▃▅·█ beats 12/23very easy · avg 86%▇ 0.6%blunt · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs 5.5 GB, NVIDIA only · from github.com/ollaya-dev
    ollaya run jeb:4b --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 96%

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 runs13Apache-2.0
prior · pull toward the middle
weighted average= 51.8

$ 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