HEAD TO HEAD
Nokia: anyjev and Supersonic Labs: julia-1, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | nokia/anyjev | supersonic-labs/julia-1 |
|---|---|---|
| Summary | A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched. | 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, classify, route | choice, score, noul, classify, route |
| Architecture | anyjev | julia |
| Fine-tuned from | qwen/qwen3-8b | jhu-clsp/mmbert-small |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 77.1% | 73.2% |
| Calibration error | 0.034 | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question | typed-decisions test set (400 cases, 2,000 questions) |
| Latest version | 0.2.0 | 1.0.0 |
| Variants | — | julia, tests, scripts, metrics, encoder, tokenizer |
| Size of latest version | — | 583.4 MB |
| Files | 0 | 40 |
| Downloads | 0 | 849 |
| Stars | 1 | 1 |
| Tags | system-one, qwen, training-free, calibrated, vllm, 8b | system-one, encoder, mmbert, multilingual, cpu, 144m |
| Updated | Oct 25, 2026 | Nov 17, 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.
anyjev is from Nokia and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 is the smaller model, at 144M parameters to 8.0B.
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
anyjev: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull nokia/anyjev and systemone pull supersonic-labs/julia-1 download the weights.