Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking.
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, rank, classify, route
choice, score, noul
Architecture
clm
laya
Fine-tuned from
qwen/qwen3-8b
convai-innovations/laya
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
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 clm and laya-mlx?
clm is from Contrastive-LM and laya-mlx from aac6fef. Both have open weights you can download and run. Both answer choice, score and noul questions. Only clm answers rank, classify and route. laya-mlx is the smaller model, at 421M parameters to 8.0B.
Which is more accurate, clm or laya-mlx?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, clm or laya-mlx?
clm: Free (open weights). laya-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run clm or laya-mlx locally?
Yes, both: systemone pull contrastive-lm/clm and systemone pull aac6fef/laya-mlx download the weights.
