HEAD TO HEAD
Ruoxi Qiu: canopy-jev and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | rizzo-ai-academy/rizzo-flow |
|---|---|---|
| Summary | Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens. | A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated. |
| Decides | choice, noul, score | choice, score, noul, classify, route |
| Architecture | canopy-jev | rizzo-flow |
| Fine-tuned from | qwen/qwen3.8-27b | xhtoken/spark-x2.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.4% | 64.8% |
| Calibration error | — | 0.112 |
| Valid action rate | — | — |
| Median latency | — | 195 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 |
| Latest version | 0.1.0 | 2026.09 |
| Variants | LICENSE, NOTICE, artifacts, licenses | lora, LICENSE |
| Size of latest version | 24.1 MB | 22.0 GB |
| Files | 11 | 17 |
| Downloads | 0 | 2 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | system-one, spark, lora, gguf, llama-cpp, 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.
canopy-jev is from Ruoxi Qiu and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, noul and score questions. Only rizzo-flow answers classify and route. rizzo-flow is the smaller model, at 4.0B parameters to 27B.
They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
canopy-jev: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.