# MiniMax M3: Self-Hosting Hardware, Scenarios and Commercial License

> Multimodal agent, coding and long-context workloads with explicit commercial-license review.

- Verified: 2026-09-12
- Released: 2026-06-01
- Canonical: https://chinaapi.ai/open-model-deployment/minimax-m3/
- Back to directory: https://chinaapi.ai/open-model-deployment/
- Machine-readable dataset: https://chinaapi.ai/data/open-model-deployment.json

## Model facts

- Vendor: MiniMax
- Parameters: approximately 428B total; approximately 23B active
- Native precision: BF16 plus official MXFP8; NVIDIA NVFP4 conversion available
- Context: 1M tokens
- Category: General and agentic foundation models
- Modalities: text, image, video → text
- Serving paths: Transformers, vLLM nightly, SGLang
- Official weights: https://huggingface.co/MiniMaxAI/MiniMax-M3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- Model documentation: https://github.com/MiniMax-AI/MiniMax-M3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment

## Deployment evidence

- **Official launch / minimum — evidence D:** A 4x RTX PRO 6000 NVFP4 recipe is under review upstream; V1 does not promote an unmerged recipe to validated minimum.
- **200-person team — evidence E:** A quantized multi-GPU worker is plausible, but the 200-seat recommendation needs measured TTFT, throughput and context mix.
- **Commercial API — evidence B:** Aggregated and disaggregated vLLM recipes are still landing; pinning a nightly build may be required.

## Scenario evidence

- **Multimodal agent workflows — Vendor-stated:** Official materials position M3 for multimodal perception and agent tasks. Source: https://github.com/MiniMax-AI/MiniMax-M3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- **Coding and tool orchestration — Public evidence:** The official release reports coding and agent evaluations. Source: https://huggingface.co/MiniMaxAI/MiniMax-M3?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- **Commercial embedded assistant — ChinaAPI inference:** Potentially suitable after the revenue, notice and attribution clauses are cleared.

## Commercial-use check

- License: MiniMax Community License — https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE?utm_source=chinaapi&utm_medium=research&utm_campaign=open-model-deployment
- MaaS / hosted service: Commercial API and hosted use are Commercial Use. Above USD 20M yearly revenue obtain prior written authorization; otherwise send the required one-time notice.
- Attribution: Prominently display Built with MiniMax M3 for commercial use.
- Prohibited uses: The license includes specified unlawful, military and harmful-use restrictions.

## Avoid or validate first

- Commercial launch before license notice and attribution review
- Stable-production serving without pinned framework versions

## Known limitations and open questions

- Stable vLLM release support was not complete at the V1 cutoff
- Do not equate a pending recipe with successful ChinaAPI reproduction

## 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.