Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
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
bekko
rizzo-flow
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
xhtoken/spark-x2.5-4b
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
5 ms
195 ms
p95 latency
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 bekko-system-one and rizzo-flow?
bekko-system-one is from Yuichi Tateno (hotchpotch) 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. bekko-system-one is the smaller model, at 395M parameters to 4.0B. bekko-system-one is licensed other; rizzo-flow, apache-2.0.
Which is more accurate, bekko-system-one or rizzo-flow?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); bekko-system-one does not, so there is no comparison to make without your own test.
Which is cheaper, bekko-system-one or rizzo-flow?
bekko-system-one: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bekko-system-one or rizzo-flow?
By their publishers’ figures, bekko-system-one answers in about 5 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run bekko-system-one or rizzo-flow locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
5.4 ms
—
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
