Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.
51.8K Pulls 1 Tag Updated 2 weeks ago
Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
141.9K Pulls 1 Tag Updated 3 weeks 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).
461.7K Pulls 2 Tags Updated 1 month ago
This experimental preview of the architecture that will underpin Qwen4.
107.2K Pulls 6 Tags Updated 1 week ago
DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.
27.6K Pulls 1 Tag Updated 1 week ago
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
2.2M Pulls 12 Tags Updated 1 month ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
6.7M Pulls 35 Tags Updated 2 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
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.
214.8K Pulls 15 Tags Updated 2 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.
171.4K Pulls 11 Tags Updated 2 weeks ago
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
511K 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.
662.2K Pulls 4 Tags Updated 4 months ago
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
345.4K Pulls 1 Tag Updated 3 months 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.
401.2K 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.
410.3K Pulls 2 Tags 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.
239K 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.
474.5K Pulls 1 Tag Updated 5 months ago
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
150.5K Pulls 8 Tags Updated 2 weeks ago
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
84.1K Pulls 1 Tag Updated 1 month ago
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.
113.1K Pulls 7 Tags Updated 2 weeks ago