Nanbeige/Nanbeige4-3B-Thinking-2511

Text Generation • 4B • Updated 27 days ago • 6.68k • 169

Note Outperforms Qwen3 4B Thinking at a slightly smaller size.

ServiceNow-AI/Apriel-1.6-15b-Thinker

Image-Text-to-Text • 15B • Updated 22 days ago • 8.08k • • 259

Note Doesn't usually overthink, massive improvement over the previous 1.5 model. Outstanding intelligence for a 15B model.

ByteDance/Ouro-1.4B-Thinking

Text Generation • Updated Nov 16, 2025 • 1.57k • 27

Note On par with 3-4B models.

ByteDance/Ouro-2.6B-Thinking

Text Generation • Updated Nov 16, 2025 • 168 • 69

Note On par with 4-8B models.

tiiuae/Falcon-H1R-7B

Text Generation • 8B • Updated about 16 hours ago • 2.97k • 181

Note Overthinks, but good proof-of-concept. Similar in intelligence to Apriel 1.5 Thinker (a 15B model), but not as good at agentic tasks. A bit benchmaxxed, and not so great at general knowledge. Better with RAG.

AiAsistent/Gemma3-4B-Dark-Chain-of-Thought-CoT

Text Generation • 4B • Updated 10 days ago • 102 • 8

Note Experimental model.