DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.
53.6K Pulls 1 Tag Updated 2 weeks ago
Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.
62.1K Pulls 1 Tag Updated 1 month ago
Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
154.8K Pulls 1 Tag Updated 1 month ago
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
2.7M Pulls 12 Tags Updated 2 days ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
6.8M Pulls 35 Tags Updated 3 weeks ago
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
350.1K Pulls 3 Tags Updated 1 month ago
This experimental preview of the architecture that will underpin Qwen4.
153.4K Pulls 6 Tags Updated 3 weeks ago
A self-improving family of open-source models for agentic coding
535.3K Pulls 9 Tags Updated 3 months ago
Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.
236K Pulls 15 Tags Updated 4 weeks ago
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
187.6K Pulls 11 Tags Updated 3 weeks ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
516.1K Pulls 1 Tag Updated 3 months 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.
667.3K Pulls 4 Tags Updated 5 months ago
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
357.9K Pulls 1 Tag Updated 3 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.
479.2K Pulls 48 Tags Updated 4 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, thinking and structured JSON output. Released under Apache 2.0 license.
90.8K Pulls 49 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.
416.6K Pulls 5 Tags Updated 4 months ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
426.8K Pulls 2 Tags Updated 1 month ago
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
427.7K Pulls 9 Tags Updated 5 months 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.
243.6K Pulls 1 Tag Updated 3 months ago
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
165.6K Pulls 8 Tags Updated 4 weeks ago