DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.
47.9K 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.
59.6K Pulls 1 Tag Updated 3 weeks ago
Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
151.6K Pulls 1 Tag Updated 4 weeks ago
This experimental preview of the architecture that will underpin Qwen4.
132.6K Pulls 6 Tags Updated 2 weeks ago
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
2.5M Pulls 12 Tags Updated 1 month 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
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 5 months ago
A self-improving family of open-source models for agentic coding
526.8K Pulls 9 Tags Updated 2 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.
230.2K Pulls 15 Tags Updated 3 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.
183.2K Pulls 11 Tags Updated 3 weeks ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
514.6K 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.
665.9K Pulls 4 Tags Updated 5 months ago
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
348.3K 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.
469.8K Pulls 48 Tags Updated 4 months ago
DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).
473.2K Pulls 2 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.
411.7K 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.
422K Pulls 2 Tags 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.
479.9K Pulls 1 Tag 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.
242.3K 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.
160.7K Pulls 8 Tags Updated 3 weeks ago