Thinking models

nemotron-cascade-2

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

tools thinking 30b

33.8K Pulls 3 Tags Updated 1 week ago

qwen3.5

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

vision tools thinking cloud 0.8b 2b 4b 9b 27b 35b 122b

3.8M Pulls 52 Tags Updated 3 hours ago

glm-4.7-flash

As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

tools thinking

925K Pulls 4 Tags Updated 2 months ago

qwen3-vl

The most powerful vision-language model in the Qwen model family to date.

vision tools thinking cloud 2b 4b 8b 30b 32b 235b

2.6M Pulls 59 Tags Updated 5 months ago

nemotron-3-super

NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

tools thinking cloud 120b

122.1K Pulls 7 Tags Updated 2 weeks ago

qwen3-next

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

tools thinking cloud 80b

450.2K Pulls 10 Tags Updated 3 months ago

nemotron-3-nano

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

tools thinking cloud 4b 30b

306.3K Pulls 9 Tags Updated 1 week ago

gpt-oss-safeguard

gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss

tools thinking 20b 120b

110.4K Pulls 3 Tags Updated 5 months ago

qwen3

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 30b 32b 235b

25.2M Pulls 58 Tags Updated 5 months ago

gpt-oss

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

tools thinking cloud 20b 120b

8.3M Pulls 5 Tags Updated 5 months ago

magistral

Magistral is a small, efficient reasoning model with 24B parameters.

tools thinking 24b

1.3M Pulls 5 Tags Updated 9 months ago

deepseek-v3.1

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking cloud 671b

515.2K Pulls 8 Tags Updated 6 months ago

deepseek-r1

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking 1.5b 7b 8b 14b 32b 70b 671b

81.3M Pulls 35 Tags Updated 8 months ago