Unverified50% confidenceEventExact time
Baidu has open-sourced the Unlimited OCR 2 model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedBaidu's UnlimitedOcr is a 3B-parameter OCR model with a context length of 32,768 tokens, built on DeepSeek OCR, replacing all decoder attention layers with Reference Sliding Window Attention (R-SWA), keeping the KV cache constant, and can transcribe dozens of pages in a single forward pass.71% similarUnverified2N redundancy means two completely independent systems backing each other up, each capable of carrying the full load, offering higher reliability but also significantly higher cost.57% similarUnverifiedOllama 0.40 keeps a backup copy for each model when loading models, causing disk usage to double on top of the original.55% similarUnverifiedExperiments published by the awareliquid team show that the O-series inference process holds memory constant at 0.381 MB when there are no session connections (at the 125M model scale).55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102913API
curl https://kongchang.com/api/v1/knowledge/claims/1102913MCP
get_claim(id=1102913)