Ouro 2.6B Thinking is an open-source language model by ByteDance. Features: 2.6b LLM, VRAM: 5.3GB, Context: 64K, License: apache-2.0.
Arxiv:2510.25741 Chain-of-thought Conversational Custom code Looped-language-model Ouro Reasoning Recurrent-depth Region:us Safetensors Thinking
Model Card on HF 🤗: https://huggingface.co/ByteDance/Ouro-2.6B-Thinking
Ouro 2.6B Thinking Parameters and Internals
| LLM Name | Ouro 2.6B Thinking |
| Repository 🤗 | https://huggingface.co/ByteDance/Ouro-2.6B-Thinking |
| Model Size | 2.6b |
| Required VRAM | 5.3 GB |
| Updated | 2026-03-27 |
| Maintainer | ByteDance |
| Model Type | ouro |
| Model Files | |
| Model Architecture | OuroForCausalLM |
| License | apache-2.0 |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.55.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Rank the Ouro 2.6B Thinking Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b