# Kimi K3: Self-Hosting Hardware, Scenarios and Commercial License

> Frontier-scale long-context multimodal and coding agent workloads where a cluster deployment is acceptable.

- Verified: 2026-09-12
- Released: 2026-07-27
- Canonical: https://chinaapi.ai/open-model-deployment/kimi-k3/
- Back to directory: https://chinaapi.ai/open-model-deployment/
- Machine-readable dataset: https://chinaapi.ai/data/open-model-deployment.json

## Model facts

- Vendor: Moonshot AI
- Parameters: 2.8T total; 104B active
- Native precision: MXFP4 routed experts; BF16 dense components; MXFP8 activations
- Context: 1M tokens
- Category: General and agentic foundation models
- Modalities: text, image, video → text
- Serving paths: vLLM, SGLang, TokenSpeed
- Official weights: https://huggingface.co/moonshotai/Kimi-K3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- Model documentation: https://github.com/MoonshotAI/Kimi-K3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment

## Deployment evidence

- **Official launch / minimum — evidence C:** Vendor documents supported engines but does not publish a smallest runnable GPU configuration.
- **200-person team — evidence E:** Not responsibly specifiable before a concurrency and context benchmark; workstation deployment is not credible.
- **Commercial API — evidence B:** NVIDIA Dynamo publishes full-1M profiles using 8x GB300 or 16x GB200 per aggregated worker; disaggregated profiles use more GPUs. Source: https://github.com/ai-dynamo/dynamo/blob/main/recipes/kimi-k3/README.md?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment

## Scenario evidence

- **Long-context coding agents — Vendor-stated:** Positioned for repository-scale coding and long-horizon agent work. Source: https://github.com/MoonshotAI/Kimi-K3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- **Multimodal document and video analysis — Vendor-stated:** Official materials expose native multimodal inputs and a 1M-token context window. Source: https://github.com/MoonshotAI/Kimi-K3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- **High-value enterprise agent workflows — ChinaAPI inference:** Best considered when model capability justifies data-center-class full-context workers.

## Commercial-use check

- License: Kimi K3 License — https://github.com/MoonshotAI/Kimi-K3/blob/main/LICENSE?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- MaaS / hosted service: Separate agreement required when a MaaS operator and affiliates exceed USD 20M aggregate revenue over any consecutive 12 months.
- Attribution: Display Kimi K3 prominently above 100M MAU or USD 20M monthly revenue.
- Exceptions: The cited requirements do not apply to internal use or use through Moonshot official products or certified inference partners.

## Avoid or validate first

- Single-workstation deployments
- Low-cost high-QPS chat without aggressive batching or distillation

## Known limitations and open questions

- No ChinaAPI hardware reproduction
- Full-context reference configurations are data-center cluster class

## Evidence boundary

Loading weights, completing a first forward pass and meeting a production latency/SLA are separate thresholds. The 200-person and commercial tiers require workload-specific measurement. License summaries are product research, not legal advice.

Generated by GENERATED BY scripts/gen_open_model_deployment.py.