Loading comparison…
COMPARE
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | akhilaaa3/jev-omni | aac6fef/laya-mlx |
|---|---|---|
| Summary | A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing. | Native MLX FP16 conversion of Laya for Apple silicon. The same ModernBERT-large encoder, decision transformer and heads, running in MLX with no PyTorch; the checkpoint Laya Studio fine-tunes from. |
| Decides | choice, noul, score, classify | choice, score, noul |
| Architecture | jev-omni | laya |
| Fine-tuned from | google/gemma-4-12b-it | convai-innovations/laya |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 87.6% | — |
| Calibration error | 0.040 | — |
| Valid action rate | — | — |
| Median latency | 83 ms | — |
| p95 latency | — | — |
| Evaluation suite | DecisionBench Medium (author's set) | — |
| Latest version | 2026.09 | 2026.09 |
| Variants | unified | encoder, tokenizer, LICENSE, NOTICE |
| Size of latest version | 22.3 GB | 807.0 MB |
| Files | 6 | 10 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, multimodal, gemma, vision, audio, 12b | system-one, mlx, apple-silicon, modernbert, conversion, 421m |
| Updated | Sep 26, 2026 | Sep 26, 2026 |