# 5-to-1: The Latency Gap Haunting Google's Newest Open Model

- slug: 5-to-1-the-latency-gap-haunting-googles-newest-open-model
- date: 2026-04-03
- category: Artificial Intelligence

On a Best Buy GPU, Google flagship open MoE model hits 11 tokens per second while Qwen 3.5 runs at 60 plus. The E2B edge model is the real story.

---