Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
19.8M Pulls 49 Tags Updated 3 weeks ago
GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
2.3M Pulls 1 Tag Updated 3 months ago
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
2.3M Pulls 1 Tag Updated 4 months ago
MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.
2.3M Pulls 1 Tag Updated 5 months ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
327.8K Pulls 1 Tag Updated 1 month ago
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.
194.3K Pulls 1 Tag Updated 1 month ago
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
403.9K Pulls 1 Tag Updated 3 months ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
290.2K Pulls 1 Tag Updated 3 months ago
Grok 4.5 is an advanced frontier AI model built by xAI in collaboration with Cursor, designed specifically for coding, agentic tasks, and complex knowledge work.
26 Pulls 1 Tag Updated yesterday
Claude Opus 4.8 is Anthropic's flagship AI model, built for complex agentic coding, multi-step reasoning, and enterprise tasks.
556 Pulls 1 Tag Updated 2 weeks ago
Gemma 4 31B (Google DeepMind) with thinking mode enabled. Best for complex reasoning, math, coding, and multi-step analysis. Knowledge cutoff: January 2025. Sampling: temperature 1.0 / top_p 0.95 / top_k 64.
559 Pulls 1 Tag Updated 3 months ago
2 Pulls 1 Tag Updated 1 month ago
A reasoning-focused AI. optimized for epistemic honesty, safety, and human-aligned decision making. Designed to prioritize accuracy over creative embellishment and maintain transparency in uncertain contexts
121 Pulls 1 Tag Updated 2 months ago
TrAi is a type of Ai model built for performance It adheres to safety in every single letter of your responses or it's replies All of its earlier models like TrAi 2 ChEg or TrAi IMS are gone, TrAi has beat performance out of everything but costs only tiny
1 Pull 1 Tag Updated 17 hours ago
A sample and cloned model for testing purpose only