TokenRhythm has released NeoHorse-1-4B, a 4 billion parameter causal language model. This model is an initial prototype designed for recursive self-improvement and is fine-tuned from Qwen3.5-4B. NeoHorse-1-4B is optimized for agent harnesses, tool use, coding, and instruction following, with instructions provided for integration via libraries like Transformers, vLLM, and SGLang, as well as through Docker. AI
IMPACT This model's focus on recursive self-improvement and agent harnesses could influence future AI development methodologies.
RANK_REASON Release of a new language model from a non-frontier lab, with details on its architecture and intended use. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
- Docker
- Hugging Face
- OpenAI
- Qwen3.5-4B
- SGLang
- TokenRhythm
- TokenRhythm/NeoHorse-1-4B
- transformers
- vLLM
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
