Sitemap

Site pages · 2

Registry index browse, search, sort and filter all models
FAQ quickfacts terms explained: context window, modalities, size, pulls, tags, usage level, updated

Model pages · 19 model pages

deepseek-v4-flash:cloud 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.
deepseek-v4-pro:cloud DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
gemma4:cloud 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.
glm-5.1:cloud 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.
glm-5.2:cloud GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
glm-5.3-flash:cloud Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
glm-5.3:cloud Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.
gpt-oss:120b-cloud OpenAI's larger open model, strong reasoning and agentic use
gpt-oss:20b-cloud OpenAI's smaller open model, low latency
kimi-k2.6:cloud 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.
kimi-k2.7-code:cloud 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.
kimi-k3:cloud Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
minimax-m2.7:cloud MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
minimax-m3:cloud MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
mistral-large-3:cloud A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
nemotron-3-nano:cloud Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
nemotron-3-super:cloud NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
nemotron-3-ultra:cloud NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
qwen3.5:cloud Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

Every model page is generated automatically from ollama.com · Retrieved 2026-08-29