Nous ResearchNomos
Nomos 1
Nomos 1 specializes Qwen3-30B-A3B-Thinking-2507 for mathematical problem solving and natural-language proofs.
Training and model behavior
The model is designed to run with the released Nomos reasoning harness. The card recommends no system prompt. Its reported Putnam performance includes the harness, so that result describes a complete inference procedure.Nomos 1 model card
Working with this model
Practical guidance. Compare the model alone and the full harness separately. Have a qualified reviewer check proof validity; a fluent argument can still omit a required step.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | NousResearch/nomos-1 |
| Context window | 262,144 tokens Configured position limit; practical serving limits depend on the runtime. Nomos 1 configuration |
| Base model | Qwen/Qwen3-30B-A3B-Thinking-2507Nomos 1 model card |
| Repository license label | apache-2.0Nomos 1 model card |