How GPU Architecture and Memory Bandwidth Dictate LLM Inference Speed

blaizedsouza · x · 2026-08-16

A deep dive into GPU architecture explains that faster GPUs don't always yield higher token generation speeds. Arithmetic units are rarely the bottleneck; they spend most time waiting for data. Memory bandwidth, which grows much slower than compute capability, is often the limiting factor.

For instance, the H100 offers 989 TFLOPS at 16-bit precision but only 3.35 TB/s of memory bandwidth, meaning 295 operations per byte. This context clarifies why techniques like quantization and speculative decoding are critical. The post also highlights the open-source project "time-to-first-token", a 10-week roadmap for learning LLM inference serving and optimization.

Original post →

More from Infra

Infra channel →