Compared on repository metadata · updated 2 November 2026
decider-2b-vision vs laya
Both are decision models. What separates them is licence, architecture, size and whether anyone has checked the numbers. Only one of those is a matter of opinion.
Side by side
Rows marked with a dot are where the two genuinely differ. Everything here comes from each repository’s own metadata, read on 2 November 2026.
| Dimension | decider-2b-vision | laya |
|---|---|---|
| Published by | Mapika | convaiinnovations |
| Weights | Open | Open |
| Licence | apache-2.0 | apache-2.0 |
| Base model | Qwen/Qwen3.5-2B-Base | Not disclosed |
| Architecture | Decoder | Not disclosed |
| Parameters | 2.2B | 421M |
| Local formats | Original weights only | Original weights only |
| Measured by us | No | No |
| Attention | 2,018 downloads, 35 likes | 61,034 downloads, 5,883 likes |
What actually separates them
laya is 5.3 times smaller
421M against 2.2B. At high volume that gap shows up as cost and latency long before it shows up as accuracy, so the question is whether the larger one earns the difference on your decisions.
Neither has been measured by anyone independent
Both are days old and every figure in circulation about either was published by the people who trained it. The table above is what can be checked from repository metadata. Everything else about these two is currently unknown.
Settle it on your traffic
This page narrows the choice to the rows that matter. A private benchmark runs decider-2b-vision and laya on a frozen set of your own historical decisions and returns accuracy at every coverage level, so you can see which one clears your error budget.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.