Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models
57.8K Pulls 6 Tags Updated 2 weeks ago
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
15.3K Pulls 2 Tags Updated 1 week ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
58.1K Pulls 6 Tags Updated 2 weeks ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
23K Pulls 6 Tags Updated 2 weeks ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
157.4K Pulls 16 Tags Updated 2 weeks ago
The most powerful vision-language model in the Qwen model family to date.
888K Pulls 59 Tags Updated 2 months ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
5.6M Pulls 5 Tags Updated 2 months ago
Alibaba's performant long context models for agentic and coding tasks.
1.6M Pulls 10 Tags Updated 3 months ago
The current, most capable model that runs on a single GPU.
29M Pulls 29 Tags Updated 3 weeks ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
226.9K Pulls 8 Tags Updated 3 months ago
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
221.3K Pulls 10 Tags Updated 3 weeks ago
Google's most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities.
51.6K Pulls 1 Tag Updated 1 month ago
Advanced agentic, reasoning and coding capabilities.
38.8K Pulls 1 Tag Updated 2 months ago
MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.
32K Pulls 1 Tag Updated 2 months ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
25.4K Pulls 6 Tags Updated 1 month ago
A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.
23.7K Pulls 1 Tag Updated 3 months 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.
18.4K Pulls 6 Tags Updated 2 weeks ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
16.7K Pulls 1 Tag Updated 1 month ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
7,904 Pulls 1 Tag Updated 1 week ago
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
6,618 Pulls 1 Tag Updated 3 weeks ago
Advancing the Coding Capability
4,670 Pulls 1 Tag Updated 1 week ago
Exceptional multilingual capabilities to elevate code engineering
2,957 Pulls 1 Tag Updated 1 week ago