Unverified50% confidenceFactExact time

Even with the frequency locked at 1,200 MHz, 29% of sampling points still hit the 70W power limit once the T4 heated up.

1

Sources

50%

Confidence

Long-term

Relevance

10/16/2026

First Seen

Sources

Cloud T4 Falls Short of Spec: Gemma 4 Decoding Slows 7% Due to Heat

Related Entities

NVIDIA T4product

Related Claims

UnverifiedTaking a 70B BF16 model as an example, generating one token requires reading approximately 140 GB of weights, and when fully utilizing the H100's 3.35 TB/s memory bandwidth, the per-token latency is at least 42 milliseconds, with a theoretical TPS upper limit of approximately 24 tokens/second.68% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1047197

API

curl https://kongchang.com/api/v1/knowledge/claims/1047197

MCP

get_claim(id=1047197)