Laguna XS 2.1 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.
48.8K Pulls 4 Tags Updated 2 weeks ago
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.
26.8K Pulls 7 Tags Updated 1 month ago
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
228.3K 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.
151.2K Pulls 1 Tag Updated 1 month ago
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
26K Pulls 1 Tag Updated 1 month ago
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
66.5K Pulls 5 Tags Updated 1 month ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
262.5K Pulls 1 Tag Updated 1 month 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.
4,492 Pulls 16 Tags Updated 1 month 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.
187.2K Pulls 5 Tags Updated 2 months 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.
257.6K 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.
618.9K Pulls 4 Tags Updated 2 months 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.
244.6K Pulls 1 Tag Updated 2 months ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
244.2K Pulls 1 Tag Updated 2 months 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.
21.3K Pulls 7 Tags Updated 2 months ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
4.2M Pulls 30 Tags Updated 1 month 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
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.
382.8K Pulls 1 Tag Updated 2 months ago
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
133.7K Pulls 3 Tags 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
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.
18.6M Pulls 49 Tags Updated 2 weeks ago