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 | aac6fef/laya-multilingual-mlx | together-ai/tev1 |
|---|---|---|
| Summary | Native MLX FP16 conversion of Laya's multilingual checkpoint (mmBERT) for Apple silicon, with a 1,024-token context. The base for multilingual fine-tunes in Laya Studio. | Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published. |
| Decides | choice, score, noul | choice, classify, route |
| Architecture | laya | tev |
| Fine-tuned from | convaiinnovations/laya-multilingual | qwen/qwen3.5-4b |
| License | apache-2.0 | Unspecified — weights licence being finalised |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Together AI |
| Input price | — | $0.042/MTok |
| Decision accuracy | — | 88.0% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | — | Together development set (reused, not held out) |
| Latest version | 2026.09 | 2026.09 |
| Variants | encoder, tokenizer, LICENSE, NOTICE | — |
| Size of latest version | 646.8 MB | 8.7 GB |
| Files | 10 | 10 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, mlx, apple-silicon, multilingual, conversion, 322m | system-one, qwen, lora, together, 4b |
| Updated | Sep 26, 2026 | Sep 26, 2026 |