Gemma 4 26B on v6e-4 Turbo-Stable Benchmark

<p><em>This is a submission for the <a href="https://dev.to/challenges/google-gemma-2026-05-06">Gemma 4 Challenge: Build with Gemma 4</a></em></p> <p>model: Gemma-4-31B</p> <h1> 🚀

<a href="https://news.ycombinator.com/item?id=48922434">Comments</a>

<!-- SC_OFF --><div class="md"><p>I tested two llama.cpp builds on the same <strong>Qwen3.6-27B-NVFP4</strong> model.</p> <p><code>llama-bench</code> reports the model label as

<!-- SC_OFF --><div class="md"><p>Got Qwen 3.5 27B to 1,103,941 tok/s on 12 nodes with 96 B200 GPUs.</p> <p>At that rate you process 50,000 insurance policy documents in hours

Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.