Unverified50% confidenceFactExact time
ERNIE 5.5 Flash Base was pre-trained on 33.5 trillion tokens and supports a maximum context of one million tokens.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Baidu's ERNIE 5.5 Flash Base Goes Open Source, Images 2.6 Dual Versions Hit the API
bilibili白洛奇_qi11/5/2026
Related Entities
Related Claims
UnverifiedThe project consumed approximately 1 billion tokens of computing resources during the training and debugging phases.60% similarUnverifiedMeta's LLaMA 3 was trained on more than 15 trillion tokens.59% similarUnverifiedNCP-ArchPreview scales to 8.9 billion parameters and is trained on 5.73 trillion tokens of the Dolma-3 dataset.59% similarPartially VerifiedMuse Spark Open has 816 billion total parameters, activates 42 billion parameters per token, and has a context window of 1 million tokens.59% similarUnverifiedThe author developed GFX1151 Engine primarily with assistance from large models such as Kimi and ChatGPT; after independently reaching approximately 600 tokens/s, further improvement proved difficult, and the speed was ultimately raised to 800–1,000 tokens/s by reverse-engineering and referencing the Hologen Flash Server approach.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1140881API
curl https://kongchang.com/api/v1/knowledge/claims/1140881MCP
get_claim(id=1140881)