Model ID
XiaomiMiMo/MiMo-V2-Flash
Capabilities
MiMo V2 Flash
MiMo V2 Flash is a large-scale Mixture-of-Experts (MoE) language model developed by Xiaomi for high-speed reasoning, coding, and agentic workflows. The model features 309B total parameters with 15B activated, built on a 48-layer transformer architecture with 64 attention heads and a 4,096 hidden size. It utilizes a hybrid attention design that interleaves Sliding Window Attention and Global Attention in a 5:1 ratio, significantly reducing KV-cache memory while maintaining long-context performance. The model supports up to a 256K token context window and integrates Multi-Token Prediction (MTP) to accelerate generation throughput.
About this model
MiMo V2 Flash is a large-scale Mixture-of-Experts (MoE) language model developed by Xiaomi for high-speed reasoning, coding, and agentic workflows. The model features 309B total parameters with 15B activated, built on a 48-layer transformer architecture with 64 attention heads and a 4,096 hidden size. It utilizes a hybrid attention design that interleaves Sliding Window Attention and Global Attention in a 5:1 ratio, significantly reducing KV-cache memory while maintaining long-context performance. The model supports up to a 256K token context window and integrates Multi-Token Prediction (MTP) to accelerate generation throughput.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (XiaomiMiMo/MiMo-V2-Flash). Released under MIT. Further reading: Paper · Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
B200
1,440 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Due to the model architecture having only 4 Key-Value heads, the maximum supported Tensor Parallelism is 4.
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on B200 · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
NVIDIA HGX B200
Unlock Next-Generation AI Power on Vultr Cloud GPU