Unverified50% confidenceFactExact time
MiMo Pro is a 1-trillion-parameter, 2-billion-active-parameter MoE model that requires approximately 500 GB of VRAM—about 8 H100s—to run at 4-bit quantization.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
UnverifiedMiMo-V2.6 supports a context length of up to 1 million (1M) tokens.77% similarUnverifiedMiMo-V2.5 is a large model with over 300 billion (300B+) parameters.77% similarUnverifiedMiMo V2.6 Pro has 1.02T total parameters and 42B activated parameters.70% similarUnverifiedMiMo V2.6 Flash has 310B total parameters and 15B activated parameters, with a speed nearly twice that of Pro.69% similarUnverifiedOn a task with one million input tokens, thirty thousand output tokens, and a 99% cache hit rate, MiMo-V2.6 Flash costs less than half of Qwen 3.8 Flash.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973519API
curl https://kongchang.com/api/v1/knowledge/claims/973519MCP
get_claim(id=973519)