HEAD TO HEAD
Andy Zhang: ajev and Supersonic Labs: julia-1, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | supersonic-labs/julia-1 |
|---|---|---|
| Summary | An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass. | A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU. |
| Decides | choice, score, noul | choice, score, noul, classify, route |
| Architecture | ajev | julia |
| Fine-tuned from | google/gemma-4-26b-a4b-it | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 73.2% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 49 ms | — |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | typed-decisions test set (400 cases, 2,000 questions) |
| Latest version | 2026.09 | 1.0.0 |
| Variants | — | julia, tests, scripts, metrics, encoder, tokenizer |
| Size of latest version | 141.9 MB | 583.4 MB |
| Files | 3 | 40 |
| Downloads | 0 | 863 |
| Stars | 0 | 1 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, encoder, mmbert, multilingual, cpu, 144m |
| Updated | Oct 7, 2026 | Nov 22, 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.
ajev is from Andy Zhang and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. julia-1 is the smaller model, at 144M parameters to 26B.
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); ajev does not, so there is no comparison to make without your own test.
ajev: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull andy-zhang/ajev and systemone pull supersonic-labs/julia-1 download the weights.