HEAD TO HEAD
Omar (kouhxp): gutsy and Jared Palmer: kev, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | kouhxp/gutsy | jared-palmer/kev |
|---|---|---|
| Summary | 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. | An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | gutsy | kev |
| Fine-tuned from | qwen/qwen3.5-0.8b | qwen/qwen3.5-4b-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 73.2% | 83.8% |
| Calibration error | — | 0.042 |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | JevBench public set (231 items; 169 correct), the maker's own run with Q8_0 | transfer-v4 (locked, out of domain) |
| Latest version | 0.4.0 | 2026.09 |
| Variants | LICENSE, gutsy-inference | — |
| Size of latest version | 1.2 GB | 152.2 MB |
| Files | 24 | 11 |
| Downloads | 0 | 1 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, gguf, llama-cpp, cpu, 0.8b | system-one, qwen, lora, pointer-head, 4b |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
gutsy is from Omar (kouhxp) and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. gutsy is the smaller model, at 800M parameters to 4.0B.
They report on different suites — gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0, kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
gutsy: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull kouhxp/gutsy and systemone pull jared-palmer/kev download the weights.