Overview
Description
Kimi K3 is an open-weight Mixture-of-Experts (MoE) foundation model from Moonshot AI featuring a 1-million-token context window and native visual understanding. Engineered specifically for complex agentic workflows, it enables deep document synthesis, autonomous tool invocation, and multi-turn planning at enterprise scale.
Technical scorecard
License
Apache-2.0
Commercial use
Yes
OpenAI-compatible API
Yes
REST API
Yes
Fine-tuning support
No
Quantization support
safetensors
Docker available
No
GUI / no-code available
No
Telemetry
None
Offline after setup
Yes
Data & Privacy
Does it send data online?
After setup, this listing is marked as usable offline. Confirm network behavior against the upstream project before regulated deployment.
Does it store history?
Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.
License checks?
Commercial use is marked as allowed or likely allowed by the listed license.
Telemetry?
None
Last verified: Aug 24, 2026. Maintainer verification should be treated as directory guidance, not legal advice.
Planning to deploy Kimi K3?
Estimate exact GPU VRAM requirements, context limits, fine-tuning memory, and infrastructure costs for Kimi K3 before committing to hardware.
Calculate Hardware & GPU Sizing →Setup & Installation
A developer can usually get this running with standard docs.
# Start with the official project repository
# https://github.com/MoonshotAI/Kimi-k3Hardware Requirements
Works Well With