North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
1,350 Pulls 7 Tags Updated yesterday
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
23.3K Pulls 1 Tag Updated 2 days 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.
17.9K Pulls 1 Tag Updated 6 days ago
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
13K Pulls 1 Tag Updated 2 weeks ago
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
28.9K Pulls 5 Tags Updated 2 weeks ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
57.4K Pulls 1 Tag Updated 2 weeks ago
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
3,362 Pulls 13 Tags Updated 2 weeks ago
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
5,102 Pulls 13 Tags Updated 2 weeks ago
Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
509 Pulls 16 Tags Updated 1 week ago
Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.
69.8K Pulls 5 Tags Updated 1 month ago
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.
176.9K Pulls 48 Tags Updated 1 month ago
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
607.8K Pulls 4 Tags Updated 1 month ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
129.3K Pulls 1 Tag Updated 1 month ago
DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
123.1K Pulls 1 Tag Updated 1 month ago
Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
16.9K Pulls 7 Tags Updated 1 month ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
2.5M Pulls 30 Tags Updated 2 weeks ago
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
35.8K Pulls 5 Tags Updated 2 months ago
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
72.2K Pulls 9 Tags Updated 2 months 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.
2.2M Pulls 1 Tag Updated 2 months 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.
306.9K Pulls 1 Tag Updated 1 month ago