LocalClaw/LLM/MiniMax M2 (230B MoE)
Open-weight local LLM

MiniMax M2 (230B MoE)

MiniMax MoE flagship with 10B active params and 4M-token long-context. Specialised for agentic coding and tool-use. Competitive with GPT-4 class models at a fraction of the inference cost. MIT licensed.

Server-grade 192 GB RAM Q4_K_M Coding assistant
Run with LocalClaw Compare all models
Parameters
230B (10B active)
Minimum RAM
192 GB
Model size
140 GB
Quantization
Q4_K_M

Can MiniMax M2 (230B MoE) run locally?

MiniMax M2 (230B MoE) is server-grade locally. Keep it for comparison unless you have very large unified memory, multiple GPUs or remote inference.

Search for minimax-m2 in LM Studio or another GGUF-compatible runtime.

MiniMaxAI/MiniMax-M2
chatcodereasoningquality

Install path

01
Check RAM fitMinimum 192 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch minimax-m2 in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • MiniMax MoE flagship with 10B active params and 4M-token long-context. Specialised for agentic coding and tool-use. Competitive with GPT-4 class models at a fraction of the inference cost. MIT licensed.

Limitations

  • Performance depends on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • code
  • reasoning
  • quality

Capability profile

speed
5
quality
9
coding
10
reasoning
9

Technical notes

Developer
minimax
License
See model repository
Context window
Unknown tokens
Architecture
See model card

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Very large memoryMac Studio Ultra classCheck model size firstNVIDIA GB10 / server optionsMore practical alternativesCompare smaller models

Where to go next