- Giants
- SemiAnalysis
- Qwen3.5 TCO vs Interactivity

Qwen3.5 TCO vs Interactivity
SemiAnalysis's line chart drew 8.5K views on X: 0.2x its typical post and #38 of 38 SemiAnalysis charts we track by views. Read Oct 15, 2026.
What is surprising is that Google TorchTPU vLLM on TPUv7 FP8 with just 4 chips was able to beat GB300 NVL72 FP4 on performance per TCO across most of the pareto frontier. At low interactivity, gb300 fp4 still wins but at low interactivity
Make it yours
We have not read this chart's numbers yet
Its own maker appears here once its numbers are read. Until then, these are other real charts in a similar format: each data page starts from that chart's numbers and takes yours.
API
Not in the API yet
We have not read this chart's numbers yet, so the API has nothing to return for it. Charts with numbers read are on the data page, and each one can be called by id.
More from SemiAnalysis
All 38Other giants using a line chart
All 318Questions people ask
How far did SemiAnalysis's "Qwen3.5 TCO vs Interactivity" chart travel?
8,487 views, 40 likes, 4 reposts and 6 saves on X, read Oct 15, 2026. A normal post from @SemiAnalysis_ gets about 51K views.
What kind of chart is it?
A line chart. Cost per chip versus interactivity for Qwen models.
Can I use SemiAnalysis's chart?
Use the format, not the picture. The chart, logo and design belong to SemiAnalysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.


