**作者**: NGS Pilot Team **測試日期**: 2026-04-08 **測試環境**: NVIDIA RTX 3090 24GB・Ollama v0.20.3・Ubuntu 22.04 **模型**: `gemma4:e4b`（9.6GB）・`gemma4:26b`（
作者: NGS Pilot Team
測試日期: 2026-04-08
測試環境: NVIDIA RTX 3090 24GB・Ollama v0.20.3・Ubuntu 22.04
模型: gemma4:e4b（9.6GB）・gemma4:26b（18GB MoE）
TL;DR
A field report on serving Gemma 4 E2B under vLLM on AWS G5g — the only aarch64 + SM 7.5 hardware there is. No published build…
A Blog post by Nikhil K. on Hugging Face
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Google released four Gemma 4...
How to get Google's Gemma 4 26B-A4B Mixture-of-Experts model running locally — including speculative...
In the last entry I got Gemma-4's 128-expert MoE running on an inf2.24xlarge and signed off with...
This stack uses Ollama with Gemma 4 QAT to run a 12B model on a 10GB VRAM laptop GPU. The latest...
