LocalClaw/LLM/MiniMax M3 (428B/23B active)
Public model card reference

MiniMax M3 (428B/23B active)

Catalogue summary: MiniMax native multimodal MoE with 1M context and MiniMax Sparse Attention. Around 428B parameters with 23B active. Built for long-context coding, cowork and agentic workflows, with local deployment via SGLang, vLLM or Transformers. Server-grade only.

Repository editorial metadata; verify comparative claims in the linked upstream material.

Public model cardNo public GGUF verified428B (23B active)2026-06
Choose an app

Only verified options can be opened. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceModel card, licence and access details
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
Source status
Public model card
Public GGUF
Not verified
Parameters
428B (23B active)
Access
Public card

Verified source status

LocalClaw verified a public model card for MiniMax M3 (428B/23B active) on 2026-09-07, but no public GGUF file in that repository. The catalogue RAM and quantization fields are estimates, not a verified install path.

Only the public model card was verified; no public GGUF file was verified in that repository. Open the model card to confirm current artefacts and supported runtimes. LocalClaw does not claim a one-click LM Studio install.

Public model card (no GGUF file verified 2026-09-07): MiniMaxAI/MiniMax-M3Upstream releasePaper or model cardLicence text
chatcodereasoningagenticlong-contextmultimodalquality

Source availability

01
Open the model cardUse the verified upstream card as the source of truth for this record.
02
Inspect current filesNo public GGUF file was verified in the repository during the catalogue audit.
03
Confirm a supported runtimeChoose a local runtime only after verifying the exact artefact, licence and hardware requirements upstream.

Catalogue record

  • Family: minimax
  • Parameters: 428B (23B active)
  • Recommended quantization: BF16 / custom runtime
  • Catalogue minimum RAM: 2048 GB
  • Catalogue model size: 1700 GB
  • Tags: chat, code, reasoning, agentic, long-context, multimodal, quality

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • agentic
  • long-context
  • multimodal

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
3
quality
10
coding
10
reasoning
10

Technical notes

Developer
MiniMax AI
License
MiniMax Community License
Context window
1,000,000 tokens
Architecture
Native multimodal sparse MoE — about 428B parameters, about 23B active, MiniMax Sparse Attention for million-token context

Where to go next