A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp16: checked against the model's own answers, none changed. Not made by Convai Innovations.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
bev-decider
laya
Fine-tuned from
qwen/qwen3-0.6b
convai-innovations/laya
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.7%
—
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 bev-decider and laya-noulxp-gpu?
bev-decider is from Avishek Biswas and laya-noulxp-gpu from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya-noulxp-gpu answers classify and route. bev-decider reads up to 2K tokens of state, against 512 tokens for laya-noulxp-gpu. laya-noulxp-gpu is the smaller model, at 421M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; laya-noulxp-gpu, apache-2.0.
Which is more accurate, bev-decider or laya-noulxp-gpu?
Only bev-decider publishes an accuracy figure (74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own); laya-noulxp-gpu does not, so there is no comparison to make without your own test.
Which is cheaper, bev-decider or laya-noulxp-gpu?
bev-decider: Free (open weights). laya-noulxp-gpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or laya-noulxp-gpu locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull convai-innovations/laya-noulxp-gpu download the weights.
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
