Updated 2 November 2026
Open-source alternatives to Jev
Grouped by the reason you would actually switch, not by a leaderboard position that does not exist yet.
Jev is a hosted API. Everything below is an open-weight model you run yourself.
Replacing a hosted call with local weights trades a key, a round trip and a vendor version number for the operational cost of running a model. That is usually the right trade at volume and the wrong one while you are still finding out whether the decision is even worth automating.
277 of the 344 projects in our directory reference Jev, so there is working code to read before you commit either way. Full detail on the model itself is on its page.
Choosing between them
Every group below is built from facts you can check on the model’s own card: licence, format, architecture and size. To see which candidate holds up against Jev on your traffic, a private benchmark runs them side by side on your own historical decisions.
Licensed for commercial use
Apache-2.0 or MIT. Start here if this is going into a product, because licence rules a model out faster than any benchmark.
laya
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
JEV-27B-VL
Qwen3.8-27B fine-tuned to return typed decisions, 28B parameters.
JEV-35B
Qwen3.5-35B-A3B fine-tuned to return typed decisions, 36B parameters.
Qwen-2.5-1B-RLCD
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
JEV-27B
Qwen3.8-27B fine-tuned to return typed decisions, 27B parameters.
AutoTrust-JEV-27B-v1.1
AutoTrust-JEV-27B-v1.1, an open-weight model published to return typed decisions, 27B parameters.
Ship in a runnable local format
GGUF, MLX, ONNX or Core ML builds exist, so you can run one without assembling a Python serving stack first.
Qwen-2.5-1B-RLCD
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
jev
jev, an open-weight model published to return typed decisions, 882M parameters.
raya
laya fine-tuned to return typed decisions, 322M parameters.
Bonsai-JEV
Ternary-Bonsai-2-27B-gguf fine-tuned to return typed decisions, 27B parameters.
wolf-defender-jev
mmBERT-small fine-tuned to return typed decisions, 151M parameters.
archai-jev-zagreus-0.4b-ita
zagreus-0.4B-ita fine-tuned to return typed decisions, 438M parameters.
Smaller and cheaper to run
Fewer parameters, so cheaper per decision at volume. Whether they give up accuracy for it is unmeasured.
laya
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
JEV-27B-VL
Qwen3.8-27B fine-tuned to return typed decisions, 28B parameters.
JEV-35B
Qwen3.5-35B-A3B fine-tuned to return typed decisions, 36B parameters.
JEV-27B
Qwen3.8-27B fine-tuned to return typed decisions, 27B parameters.
AutoTrust-JEV-27B-v1.1
AutoTrust-JEV-27B-v1.1, an open-weight model published to return typed decisions, 27B parameters.
laya-multilingual
The only multilingual decision model we have found, a 322M encoder on mmBERT. Also the one our English-only test set cannot say anything useful about.
Compare them head to head
Jev vs laya
Side by side on licence, architecture, size and what has been measured.
Jev vs JEV-27B-VL
Side by side on licence, architecture, size and what has been measured.
Jev vs JEV-35B
Side by side on licence, architecture, size and what has been measured.
Jev vs Qwen-2.5-1B-RLCD
Side by side on licence, architecture, size and what has been measured.
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.