Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
23.4K Pulls 1 Tag Updated 6 days ago
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
381 Pulls 3 Tags Updated 7 hours ago
A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
153.7K Pulls 13 Tags Updated 2 weeks ago
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
116.8K Pulls 4 Tags Updated 1 week ago
LFM2.5 is a new family of hybrid models designed for on-device deployment.
29.1K Pulls 5 Tags Updated 1 week ago
The most powerful vision-language model in the Qwen model family to date.
1.3M Pulls 59 Tags Updated 3 months ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
353.6K Pulls 16 Tags Updated 1 month ago
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
303.8K Pulls 6 Tags Updated 1 month ago
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
298.1K Pulls 10 Tags Updated 1 month ago
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
629.9K Pulls 17 Tags Updated 3 months ago
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
492.1K Pulls 12 Tags Updated 4 months ago
Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models
143.7K Pulls 6 Tags Updated 1 month ago
EmbeddingGemma is a 300M parameter embedding model from Google.
469.1K Pulls 5 Tags Updated 4 months ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
125.1K Pulls 6 Tags Updated 1 month ago
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
116.1K Pulls 15 Tags Updated 1 month ago
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
144.3K Pulls 3 Tags Updated 2 months ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
311.8K Pulls 8 Tags Updated 4 months ago
69.3K Pulls 10 Tags Updated 1 month ago
Google's most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities.
95.7K Pulls 1 Tag Updated 2 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
63.3K Pulls 6 Tags Updated 1 month ago