Tracked as a source-level fact for technical comparison.
Source-verified model profile · 1 October 2026
Kimi K3
Kimi K3 is an open-weight model from Moonshot AI focused on long-horizon coding, knowledge work and multimodal agents. This profile separates model facts, license terms, infrastructure feasibility and European data-residency questions.
OPEN WEIGHTSKIMI K3 LICENSEASIAEU SELF-HOSTING POSSIBLE
Direct answer
What is Kimi K3?
Kimi K3 is a Kimi K3 open-weight model published by Moonshot AI. The current profile records 2.8T total, 104b active/token, 1,048,576 of context and Text + image → text. The recorded license is Kimi K3 License.
Its practical focus is long-horizon coding, knowledge work and multimodal agents. Treat the exact checkpoint and revision as the deployable entity; quantization and serving layers can materially change memory, throughput and exposed features.
Official model source ↗Provider origin🇨🇳 China
RegionAsia
Parameters2.8T total
Active compute104B active/token
Context1,048,576
ModalitiesText + image → text
LicenseKimi K3 License
VerificationSource-verified · 2026-10-01
Architecture & capability
Publisher-documented signals.
Tracked as a source-level fact for technical comparison.
Tracked as a source-level fact for technical comparison.
Tracked as a source-level fact for technical comparison.
Tracked as a source-level fact for technical comparison.
License & commercial use
Separate downloadability from rights.
The recorded license is Kimi K3 License. Open weights describe availability of parameters; they do not automatically settle commercial use, redistribution, derivative works, attribution, patent terms or a separate acceptable-use policy.
For production, retain the exact license/revision alongside the deployed checkpoint and confirm whether provider-specific conditions apply.
Technical comparison only — not legal advice.
Deployment
Hardware and runtime reality.
Large datacenter / multi-GPU class. The model's 2.8T total parameter pool dominates storage and sharding requirements.
The official weights are published for independent deployment; practical serving requires a large distributed inference stack.
Context length, batch size, KV cache, quantization, expert routing and multimodal encoders can shift memory and throughput substantially.
EU deployment lens
Provider origin is not data residency.
EU/EEA self-hosting is technically possible when the downloadable weights, runtime and connected services are operated on infrastructure selected by the deployer.
The 🇨🇳 flag describes provider origin: China. It does not say where prompts, documents, embeddings, logs, monitoring or backups are processed.
Self-hosting does not itself establish GDPR or AI Act compliance. Map the complete data flow and the organization's legal role.
EU deployment & data-residency guide →FAQ
Common questions.
What is Kimi K3?
Kimi K3 is an open-weight model from Moonshot AI focused on long-horizon coding, knowledge work and multimodal agents.
Can Kimi K3 be self-hosted?
Yes, the published weights enable independent deployment where the license permits it. Hardware feasibility depends on precision, context and serving topology.
Can Kimi K3 run in the EU?
Technically yes when the complete inference stack and connected data services are operated on EU/EEA infrastructure.
Can Kimi K3 be used commercially?
The recorded license is Kimi K3 License. Review the exact official terms and any separate use policy before production.
Primary source
Verify the exact checkpoint.
The official model card remains authoritative for revision-specific architecture, files, inference settings and license links.
Moonshot AI · official model page ↗