Flame R1

Flame R1 is a next-generation merged AI model built for the world. Combining deep reasoning of DeepSeek R1 with coding excellence of Qwen2.5 Coder.

Model Details

Property Value
Created by Flame
Base Models DeepSeek-R1-Distill-Qwen-1.5B + Qwen2.5-Coder-1.5B
Merge Method SLERP
Parameters 1.5B
Languages 25+ Global
License Apache 2.0

Languages

Asia: Hindi, Chinese, Japanese, Korean, Bengali, Urdu, Thai, Vietnamese, Indonesian, Malay Europe: English, French, German, Spanish, Italian, Portuguese, Russian, Dutch, Polish, Swedish, Danish, Finnish, Norwegian Middle East: Arabic, Turkish

Capabilities

  • Deep Reasoning from DeepSeek R1
  • Code Generation from Qwen2.5 Coder
  • 25+ Global Languages
  • Friendly and Professional tone

Built by Flame for the world.

Downloads last month
16
Safetensors
Model size
2B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for FlameGpt2026/flame-r1