HEAD TO HEAD

nanojev vs rizzo-flow

Q: Can I run nanojev or rizzo-flow locally?

Yes, both: systemone pull tianyu-codings/nanojev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.

TianyuCodings: nanojev and Rizzo AI Academy: rizzo-flow, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

Both have open weights you can download and run.
Both answer choice, noul and score questions.
Only rizzo-flow answers classify and route.
nanojev is the smaller model, at 600M parameters to 4.0B.
nanojev is licensed mit; rizzo-flow, apache-2.0.

Property	tianyu-codings/nanojev	rizzo-ai-academy/rizzo-flow
Summary	A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.	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	nanojev	rizzo-flow
Fine-tuned from	qwen/qwen3-0.6b	xhtoken/spark-x2.5-4b
License	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	—	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 nanojev and rizzo-flow?

nanojev is from TianyuCodings 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. nanojev is the smaller model, at 600M parameters to 4.0B. nanojev is licensed mit; rizzo-flow, apache-2.0.

Which is more accurate, nanojev 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); nanojev does not, so there is no comparison to make without your own test.

Which is cheaper, nanojev or rizzo-flow?

nanojev: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.

Can I run nanojev or rizzo-flow locally?

Yes, both: systemone pull tianyu-codings/nanojev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.