HEAD TO HEAD
Mapika: decider and Omar (kouhxp): gutsy, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | mapika/decider | kouhxp/gutsy |
|---|---|---|
| Summary | A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11. | 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. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | decider | gutsy |
| Fine-tuned from | qwen/qwen3.5-2b-base | qwen/qwen3.5-0.8b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 75.2% | 73.2% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | Decider regression set, 28 held-out tasks (decider-2b v11) | JevBench public set (231 items; 169 correct), the maker's own run with Q8_0 |
| Latest version | v11 | 0.4.0 |
| Variants | — | LICENSE, gutsy-inference |
| Size of latest version | 5.4 GB | 1.2 GB |
| Files | 6 | 24 |
| Downloads | 71 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, gemma, rl, calibrated, 1.9b | system-one, qwen, gguf, llama-cpp, cpu, 0.8b |
| Updated | Nov 22, 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.
decider is from Mapika and gutsy from Omar (kouhxp). Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider reads up to 32K tokens of state, against 8K tokens for gutsy. gutsy is the smaller model, at 800M parameters to 1.9B.
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
decider: Free (open weights). gutsy: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull mapika/decider and systemone pull kouhxp/gutsy download the weights.