Expired80% confidenceFactTime unknown
Some of the highest-ranked models on the MTEB leaderboard, such as Google's KALM/Gemma series, are not within FastEmbed's supported range.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGoogle open-sourced the Gemma series of small models, drawing on the successful path of Meta's open release of the LLaMA series.61% similarUnverifiedGoogle's Gemma series tokenizers are implemented using the SentencePiece framework and support both BPE and Unigram algorithms.57% similarUnverifiedGoogle released the Gemma 4 series of open-source models, comprising four models of different parameter scales.56% similarUnverifiedOpen-source models such as Meta's LLaMA and Google's Gemma are both distributed through the HuggingFace platform.56% similarUnverifiedMainstream open-source models such as Meta's LLaMA and Google's Gemma make extensive use of quantization and knowledge distillation techniques55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/15680API
curl https://kongchang.com/api/v1/knowledge/claims/15680MCP
get_claim(id=15680)