Expired50% confidenceReleaseExact time
Google's open-source model Gemma 4 went live on the Cerebras inference platform, running at a speed of 1500+ tokens per second based on 31B open-source weights, achieving approximately 15x acceleration.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
Valid until: 10/14/2026(expired)
Sources
Related Claims
UnverifiedGoogle DeepMind open-sourced Gemma 4, with 31B parameters, featuring a native multimodal design that omits the traditional encoder structure.65% similarUnverifiedGoogle开源的MediaPipe框架的Hand Landmark模型基于MobileNetV2骨干网络，在标准硬件上可达每秒30帧以上的检测速度64% similarUnverifiedGoogle's Gemma 4 is released under the Apache 2.0 open-source license, can already run on devices such as the iPhone 17 Pro, and achieves a speed of 40,000 tokens per second with MLX optimization.63% similarUnverifiedGoogle Gemma团队与Hugging Face合作，组织100多个AI智能体与开发者进行为期6天的冲刺赛，将开源模型Gemma 4的推理速度提升了5倍62% similarUnverifiedA single GPT-4-level cloud inference request consumes approximately 10 times the electricity of a traditional Google search.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/527985API
curl https://kongchang.com/api/v1/knowledge/claims/527985MCP
get_claim(id=527985)