Jan-nano Technical Report
Not on the map. Why?
Abstract (arXiv)
Most language models face a fundamental tradeoff where powerful capabilities require substantial computational resources. We shatter this constraint with Jan-nano, a 4B parameter language model that redefines efficiency through radical specialization: instead of trying to know everything, it masters the art of finding anything instantly. Fine-tuned from Qwen3-4B using our novel multi-stage Reinforcement Learning with Verifiable Rewards (RLVR) system that completely eliminates reliance on next token prediction training (SFT), Jan-nano achieves 83.2% on SimpleQA benchmark with MCP integration while running on consumer hardware. With 128K context length, Jan-nano proves that intelligence isn't about scale, it's about strategy.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Jun 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Citing papers per year: 2025: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models
- 2026Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
- 2025Diversity or Precision? A Deep Dive into Next Token Prediction
- 2024Prototypical Reward Network for Data-Efficient RLHF
- 2025Kimi k1.5: Scaling Reinforcement Learning with LLMs
- 2025Reinforcement Learning on Pre-Training Data
- 2025Reinforcement Pre-Training
- 2026Reinforcement Learning with Promising Tokens for Large Language Models