The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
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, score, noul, classify, route
choice, score, noul
Architecture
decision
laya
Fine-tuned from
qwen/qwen3.5-9b
convai-innovations/laya
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
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 decision and laya-mlx?
decision is from vLLM Semantic Router and laya-mlx from aac6fef. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decision answers classify and route. decision reads up to 16K tokens of state, against 512 tokens for laya-mlx. laya-mlx is the smaller model, at 421M parameters to 9.0B.
Which is more accurate, decision or laya-mlx?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); laya-mlx does not, so there is no comparison to make without your own test.
Which is cheaper, decision or laya-mlx?
decision: Free (open weights). laya-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or laya-mlx locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull aac6fef/laya-mlx download the weights.
