MiMo-V2.5 310B — VRAM Requirements
Written by Jakub Rusinowski · Last updated September 6, 2026
How much GPU VRAM you need to run MiMo-V2.5 MiMo-V2.5 310B by Xiaomi locally, a 310B-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.
MiMo-V2.5 310B needs about 188 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 101.9 GB | 102.7 GB |
| Q3_K_M | 3.41 | 132.1 GB | 132.9 GB |
| Q4_K_M | 4.83 | 187.2 GB | 188.0 GB |
| Q5_K_M | 5.67 | 219.7 GB | 220.5 GB |
| Q6_K | 6.56 | 254.2 GB | 255.0 GB |
| Q8_0 | 8.50 | 329.4 GB | 330.2 GB |
| F16 | 16.00 | 620.0 GB | 620.8 GB |
Switch quantization in the interactive calculator, or see the full MiMo-V2.5 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.
Add this badge to your model card
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/mimo-v2-5-310b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=mimo-v2-5-310b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.