Back to Calculator
MiMo V2 Pro
HotXiaomi MiMo's 1 trillion parameter MoE reasoning model with 384 experts, revealed as "Hunter Alpha" on OpenRouter in March 2026
Model Specifications
ArchitectureTEXT
Parameters1000B
Familymimo
VRAM (Q4)500.0GB
Mixture of ExpertsActive inference parameters: 32B.
1T total with 32B active, initially revealed anonymously on OpenRouter as Hunter Alpha
Estimated Quantization Sizes
| Format | Precision | Est. VRAM | Recommendation |
|---|---|---|---|
| FP16 / BF16 | 16-bit | 2000.0 GB | Uncompressed Base |
| Q8_0High | 8-bit | 1000.0 GB | Near Lossless |
| Q6_K | 6-bit | 750.0 GB | Excellent Balance |
| Q4_K_MPopular | 4-bit | 500.0 GB | Standard Use |
Share this Model
Send this model's specs directly to your community.
Similar Models
Related Guides
How much VRAM do you really need?
A complete breakdown of quantization levels and VRAM overhead for running local models.
Best GPUs for Machine Learning in 2026
Comparing NVIDIA and AMD options for the best speed-to-dollar ratio.
GGUF vs EXL2 vs AWQ
Understanding local AI formats and which one to pick for your specific hardware.