MiniMax M2.5 — Local AI Model by MiniMax
作者： Jakub Rusinowski · 最后更新： 2026年2月15日
MiniMax's 230B MoE model scoring 80.2% on SWE-bench — technically outperforming Claude Opus 4.6 on this benchmark — at 22.7× lower cost on output tokens. Supports up to 1M token context and includes multimodal capabilities. Available under a modified MIT license requiring attribution. Primarily API-accessed but self-hostable on multi-GPU infrastructure.
Licence
| Licence | What it permits | Applies to |
|---|---|---|
Modified MIT | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | MiniMax M2.5 230B |
Hardware Requirements
| MiniMax M2.5 230B | Min 140 GB VRAM · Q4_K_M · 1,000,000 ctx · |
Recommended GPU
The cheapest GPU that runs MiniMax M2.5 locally (min 140 GB VRAM) is the Apple M2 Ultra (192 GB).
How to Run Locally
Install Ollama then run: ollama run minimax-m2-5
Minimum VRAM: 140 GB. For best results use Q4_K_M quantization.
MiniMax M2.5 — Frequently Asked Questions
How much VRAM does MiniMax M2.5 need?
MiniMax M2.5 needs about 140 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: MiniMax M2.5 230B (140 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run MiniMax M2.5 on an RTX 4090 (24 GB)?
MiniMax M2.5's smallest variant needs about 140 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for MiniMax M2.5?
Q4_K_M is the best balance of quality and VRAM for MiniMax M2.5 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run MiniMax M2.5 with Ollama?
MiniMax M2.5 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.