Back to Calculator Deploy on RunPodDeploy Now
MiMo V2 Pro
HotXiaomi MiMo's 1 trillion parameter MoE reasoning model with 384 experts, revealed as "Hunter Alpha" on OpenRouter in March 2026
Specifications
SourceArchitectureTEXT
Parameters1000B
Familymimo
VRAM (Q4)500.0G
MoE: 32B active.
1T total with 32B active, initially revealed anonymously on OpenRouter as Hunter Alpha
xiaomimoereasoningtrending
Run in the Cloud
This model requires enterprise-grade VRAM. Rent GPUs on RunPod and start generating.
Instant Cloud GPUs
Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.
Quantization Estimates
| Format | VRAM Need | Tier |
|---|---|---|
| FP16 | 2000.0 GB | Full Precision |
| Q8_0 | 1000.0 GB | High |
| Q6_K | 850.0 GB | Excellent |
| Q5_K_M | 700.0 GB | Great |
| Q4_K_M | 500.0 GB | Sweet Spot |
| Q2_K | 300.0 GB | Emergency |
Share this Model
Send these specs directly to your community.