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.
Uprelic's hosted decision API, run on GPUs in Paris. Answers noul, choice and score questions about text, JSON and up to 8 images, with a probability for every option and no generated text, on the same request shape as Jev. No weights; base model and size not disclosed.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
gutsy
strom
Fine-tuned from
qwen/qwen3.5-0.8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
73.2%
87.0%
Calibration error
—
0.033
Valid action rate
—
—
Median latency
—
136 ms
p95 latency
—
—
Evaluation suite
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 strom?
gutsy is from Omar (kouhxp) and strom from Uprelic. gutsy has open weights you can download and run; strom is only available as a hosted API. Both answer choice, score, noul, classify and route questions. strom reads up to 32K tokens of state, against 8K tokens for gutsy. gutsy is licensed apache-2.0; strom, proprietary.
Which is more accurate, gutsy or strom?
They report on different suites — gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0, strom 87.0% on JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gutsy or strom?
gutsy: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run gutsy or strom locally?
gutsy yes — systemone pull kouhxp/gutsy downloads its weights. The other is only served as a hosted API.
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
