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.
Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX.
Decides
choice, score, noul, classify, route
noul, classify
Architecture
gutsy
laya
Fine-tuned from
qwen/qwen3.5-0.8b
convaiinnovations/laya-multilingual
License
apache-2.0
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
73.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
95.4 ms
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 laya-cybersec?
gutsy is from Omar (kouhxp) and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul and classify questions. Only gutsy answers choice, score and route. gutsy reads up to 8K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is the smaller model, at 322M parameters to 800M. gutsy is licensed apache-2.0; laya-cybersec, other.
Which is more accurate, gutsy or laya-cybersec?
Only gutsy publishes an accuracy figure (73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, gutsy or laya-cybersec?
gutsy: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gutsy or laya-cybersec locally?
Yes, both: systemone pull kouhxp/gutsy and systemone pull textcortex/laya-cybersec download the weights.
—
149 ms
Evaluation suite
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
TextCortex saved run: 279 single-window inputs, PyTorch batch one
