Kimi K2
Kimi K2 is available through Ollama for local agent workflows, with support for text input. A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.
What is Kimi K2?
Kimi K2 is a local model entry from Ollama that Agent Mag tracks for install commands, available tags, modalities, and agent workflow fit. Builders can install it with the Agent Mag CLI and run it through Ollama on their own machine.
A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.
| Tag | Size | Context | Input |
|---|---|---|---|
| kimi-k2:1t-cloud | - | 256K | text |
Related local models
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 K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
Related content
Compare pricing, local installs, context windows, and modality filters across the full model catalog.
Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.
See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.