list of open-source publicly-available reasoning llms

[andre15silva]

https://huggingface.co/deepseek-ai/DeepSeek-R1

QwQ
Qwen's reasoning model with 32B parameter

• blog https://qwenlm.github.io/blog/qwq-32b-preview/
• model: https://huggingface.co/Qwen/QwQ-32B-Preview

[monperrus]

Arcee-Maestro-7B
RL trained reasoning model based on DeepSeek-R1-Distill-Qwen-7B with further GPRO training for reasoning, math and coding
https://huggingface.co/arcee-ai/Arcee-Maestro-7B-Preview

[monperrus]

OpenThinker-32B
fine-tuned reasoning model of Qwen/Qwen2.5-32B-Instruct on the DeepSeek-R1 distilled OpenThoughts-114k dataset
https://huggingface.co/open-thoughts/OpenThinker-32B

[monperrus]

Sky-T1
UC Berkeley's reasoning model with 32B parameters
https://huggingface.co/NovaSky-AI/Sky-T1-32B-Preview