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.
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
convai-innovations/laya
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
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 laya-mlx and tev1?
laya-mlx is from aac6fef and tev1 from Together AI. laya-mlx has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice questions. Only laya-mlx answers score and noul. Only tev1 answers classify and route. laya-mlx is the smaller model, at 421M parameters to 4.0B. laya-mlx is licensed apache-2.0; tev1, other.
Which is more accurate, laya-mlx or tev1?
Only tev1 publishes an accuracy figure (88.0% on Together development set (reused, not held out)); laya-mlx does not, so there is no comparison to make without your own test.
Which is cheaper, laya-mlx or tev1?
laya-mlx: Free (open weights). tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run laya-mlx or tev1 locally?
Yes, both: systemone pull aac6fef/laya-mlx and systemone pull together-ai/tev1 download the weights.
