Loading comparison…
HEAD TO HEAD
InternLM (Shanghai AI Laboratory): intern-decision and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | internlm/intern-decision | rizzo-ai-academy/rizzo-flow |
|---|---|---|
| Summary | Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature. | 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, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | intern-decision | rizzo-flow |
| Fine-tuned from | qwen/qwen3.5-4b | xhtoken/spark-x2.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 80.6% | 64.8% |
| Calibration error | — | 0.112 |
| Valid action rate | — | — |
| Median latency | 44 ms | 195 ms |
| p95 latency | 44.6 ms | — |
| Evaluation suite | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions) | LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 |
| Latest version | 2026.09 | 2026.09 |
| Variants | LICENSE, LICENSE-QWEN | lora, LICENSE |
| Size of latest version | 8.5 GB | 22.0 GB |
| Files | 19 | 17 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, multimodal, calibrated, jevbench, 4.5b | system-one, spark, lora, gguf, llama-cpp, 4b |
| Updated | Sep 30, 2026 | Sep 30, 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.
intern-decision is from InternLM (Shanghai AI Laboratory) and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. rizzo-flow is the smaller model, at 4.0B parameters to 4.5B.
They report on different suites — intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), 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.
intern-decision: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, intern-decision answers in about 44 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull internlm/intern-decision and systemone pull rizzo-ai-academy/rizzo-flow download the weights.