Nanbeige
Model · Language & code models
33B dense open model, 66.3 GB; claimed to beat Qwen 3.8 and Gemma 4 on agentic and knowledge-work benchmarks
AccessOpen weightsNeeds~8 GBDownload8 GBLicenseApache-2.0
Versions
| Version | Released | Rank |
|---|---|---|
| Nanbeige 4.3LATEST | Nov 1 | |
| Nanbeige 4.2 | Jul 23 |
Evidence
- Nov 1Claimed higher scores than Qwen 3.8 on Terminal-Bench and Deep suite
- Jul 26Nanbeige 4.2 3B looped-transformer agentic model, 8 GB, claimed to beat Gemma 4 and Qwen 3.5 4B/9B on agentic and coding benchmarks
- Jul 26Vendor charts show it topping agent and reasoning benchmarks over Qwen3.5-9B and Gemma 4 12B; Gemma slightly ahead on SciCode
- Jul 23Looped transformer reuses one layer's weights over several passes, aiming for larger-model reasoning depth without extra parameters
- Jul 23Via Hermes Agent it found and fixed a planted Redis pub/sub channel bug in a FastAPI app, verified end-to-end, but took about an hour