Written by Jakub Rusinowski · Last updated February 15, 2026
How much GPU VRAM you need to run MiniMax M2.5 MiniMax M2.5 230B by MiniMax locally, a 229.9B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
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 | 138.8 GB | 139.6 GB |
| Q5_K_M | 5.67 | 162.9 GB | 163.7 GB |
| Q6_K | 6.56 | 188.5 GB | 189.3 GB |
| Q8_0 | 8.50 | 244.3 GB | 245.1 GB |
| F16 | 16.00 | 459.8 GB | 460.6 GB |
Switch quantization in the interactive calculator, or see the full MiniMax M2.5 model page.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
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?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=minimax-m2-5-230b)
Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.