Claude Code with Anthropic API Compatibility
Ollama is now compatible with the Anthropic Messages API, making it possible to use tools like Claude Code with open models running locally.
🧪 Beta Feature - Ollama Models News
This page is currently in beta. We're curating the latest Ollama model releases and updates to keep you informed. Your feedback helps us improve!
🌟 Featured Models
Discover the most popular and capable Ollama models currently available, hand-picked for ReactorAI users.
nemotron-3-nano
A new standard for efficient, open, and intelligent agentic models. NVIDIA's latest offering for powerful reasoning at 30B parameters.
Tools
Thinking
Cloud
30B
devstral-2
A 123B model that excels at complex tool use and software engineering tasks, perfect for powering coding agents.
Tools
Cloud
123B
qwen3-vl
The most powerful vision-language model in the Qwen family with strong multimodal reasoning from 2B up to 235B variants.
Vision
Tools
Thinking
2B-235B
ministral-3
Mistral's models designed for edge deployment on a wide range of hardware with vision and tool support.
Vision
Tools
Edge
3B-14B
functiongemma
Specialized version of Google's Gemma 3 270M model fine-tuned for function calling. Perfect for lightweight tool use.
Tools
Lightweight
270M
olmo-3
Fully open, state-of-the-art language models by AI2 trained on Dolma 3. Available in 7B and 32B variants.
Open Source
7B
32B
🔥 Latest Ollama Model News
Stay up-to-date with the newest Ollama model releases, updates, and community highlights. ReactorAI brings you curated news about the AI models that matter most to our community.
OpenAI Codex with Ollama
Open models can now be used with OpenAI's Codex CLI through Ollama. Codex can read, modify, and execute code using models such as gpt-oss:20b, gpt-oss:120b.
OpenAI gpt-oss-safeguard
Ollama partners with OpenAI and ROOST to bring gpt-oss-safeguard reasoning models for safety classification. Available in 20B and 120B sizes under Apache 2.0 license.
New Coding Models & Integrations
GLM-4.6 and Qwen3-coder-480B are available on Ollama's cloud service. Qwen3-Coder-30B updated for faster, more reliable tool calling in Ollama's new engine.
Qwen3-VL Vision Model
Ollama now supports Alibaba's Qwen3-VL, the most powerful vision-language model in the Qwen family with robust multimodal reasoning capabilities.
NVIDIA DGX Spark Support
The latest NVIDIA DGX Spark is here! Ollama has partnered with NVIDIA to ensure it runs fast and efficiently out-of-the-box for enterprise deployments.
🚀 Try These Models with ReactorAI
All featured models work seamlessly with ReactorAI. Download the app and start exploring these powerful AI models today!