Omar (kouhxp)'s CPU decision model: a Qwen3.5-0.8B fine-tune shipped as GGUF for llama.cpp that answers yes/no, choice and score questions with a probability per option plus a 'none of these' reject probability, served by a local Jev-style HTTP runtime.
SimpleJev's LoRA adapters and pointer head that turn an open model into a typed-decision model: given a state, a question and the options, it returns a probability for every option without generating text. This entry is the Qwen3.8-27B release; the others are linked.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
gutsy
jevany
Fine-tuned from
qwen/qwen3.5-0.8b
qwen/qwen3.8-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
86.0%
Calibration error
—
0.026
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
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.
Questions
What is the difference between gutsy and jevany?
gutsy is from Omar (kouhxp) and jevany from SimpleJev. Both have open weights you can download and run. Both answer choice, score and noul questions. Only gutsy answers classify and route. gutsy is the smaller model, at 800M parameters to 27B.
Which is more accurate, gutsy or jevany?
They report on different suites — gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0, jevany 86.0% on SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gutsy or jevany?
gutsy: Free (open weights). jevany: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gutsy or jevany locally?
Yes, both: systemone pull kouhxp/gutsy and systemone pull simplejev/jevany download the weights.
Evaluation suite
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own)