# N-Q-26M-JEV decision model by Q Project

> N-Q-26M-JEV scores Russian and English decisions with small local weights. Check the 1110 update, truncation limits and commercial licence terms.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is N-Q-26M-JEV by Q Project?

[N-Q-26M-JEV](<https://decisionmodels.ai/models/nq-jev>): A small Russian/English decision model with a custom hybrid backbone and decision head.

[N-Q-26M-JEV facts](<https://decisionmodels.ai/models/nq-jev>)

[Source](<https://huggingface.co/q-project/N-Q-26M-JEV-1110>)

### Who makes N-Q-26M-JEV?

[N-Q-26M-JEV](<https://decisionmodels.ai/models/nq-jev>): Q Project

[N-Q-26M-JEV facts](<https://decisionmodels.ai/models/nq-jev>)

[Source](<https://huggingface.co/q-project/N-Q-26M-JEV-1110>)

By Q Project · Hugging Face weight release: 2026-11-10 · OPEN

A small Russian/English decision model with a custom hybrid backbone and decision head. The 1110 checkpoint adds toxicity and profanity training. It scores supplied options, with reversed-order averaging enabled by default; that serving choice uses two orders.

## Facts

- Size: The card lists 29.7M parameters plus 16.8M n-gram parameters, despite the 26M name
- Inputs: Russian and English text; choice, yes/no and score questions
- Limits: Reads the first 1,536 state tokens; training-family wording is recommended
- Access: Transformers custom code; safetensors and QPACK files
- Licence: Q Project Model License 1.0: free non-commercial use; commercial use, including internal use, needs a paid licence. Company evaluation is allowed for up to 90 days without production or customer use.
- Data terms: The card identifies non-commercial ANLI data and toxicity data without a stated licence; third-party terms still apply

## Claims and sources

- **VENDOR-REPORTED**: The maker reports 45.9 on the 231-task public [JevBench](<https://decisionmodels.ai/jevbench>) v1.2 run, down from 46.3 for 1027. Its reported Russian/English toxicity accuracies are 96.1%/90.1%; harmless English uses of violent words remain failure cases. These task results do not establish general reasoning ability. [source](<https://huggingface.co/q-project/N-Q-26M-JEV-1110>)

## Links

- [Source: Card and weights](<https://huggingface.co/q-project/N-Q-26M-JEV-1110>)
- [Source: Licence](<https://huggingface.co/q-project/N-Q-26M-JEV-1110/blob/main/LICENSE>)
- [Source: Runtime](<https://huggingface.co/q-project/N-Q-26M-JEV-1110/blob/main/modeling_nq4.py>)

## Related projects

No related projects are listed in the registry.