Written by Jakub Rusinowski · Last updated July 21, 2026
How much GPU VRAM you need to run MiniMax M2.5 MiniMax M2.5 230B by MiniMax locally, a 230B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
MiniMax M2.5 230B needs about 140 GB VRAM at Q4_K_M.
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 75.6 GB | 76.4 GB |
| Q3_K_M | 3.41 | 98.0 GB | 98.8 GB |
| Q4_K_M | 4.83 | 138.9 GB | 139.7 GB |
| Q5_K_M | 5.67 | 163.0 GB | 163.8 GB |
| Q6_K | 6.56 | 188.6 GB | 189.4 GB |
| Q8_0 | 8.50 | 244.4 GB | 245.2 GB |
| F16 | 16.00 | 460.0 GB | 460.8 GB |
Switch quantization in the interactive calculator, or see the full MiniMax M2.5 model page.
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/minimax-m2-5-230b)
Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.