Expired50% confidenceFactExact time
Gemma 4 E2B runs natively on the Tensor G5's TPU, rather than on traditional CPUs or GPUs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026(expired)
Sources
Related Claims
UnverifiedGoogle released Gemma 4 E2B for TPU, an open model built specifically for the Tensor G5 chip in the Pixel 10 series.77% similarUnverifiedGemma 4 1.2B can run smoothly on the Xiaomi 15 Pro in GPU mode.73% similarUnverifiedTensor G4的TPU模块可在本地以低功耗运行专为Pixel优化的轻量级语言模型67% similarUnverifiedNative FP8 hardware acceleration was first implemented in the fourth-generation Tensor Cores of the NVIDIA Hopper architecture (H100, 2022), with a peak throughput of 3958 TFLOPS.66% similarUnverifiedFP8 is a low-precision computing format natively supported by the Blackwell architecture, including two variants—E4M3 and E5M2—and the Tensor Core's FP8 compute throughput is twice that of FP16.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/560345API
curl https://kongchang.com/api/v1/knowledge/claims/560345MCP
get_claim(id=560345)