QAT 权重让 Gemma 4 在更低内存下运行，适合在本地或边缘设备部署大模型的开发者，可以直接用 Ollama 命令体验。
Ollama 宣布 Gemma 4 的量化感知训练（QAT）权重现已可用。这些权重在保持模型质量的同时，显著降低了内存需求。用户可以通过 Ollama 直接运行多个 Gemma 4 变体，包括 e2b、e4b、12B、26B 和 31B 等版本。Google Gemma 团队也在 Hugging Face 上发布了所有 Gemma 4 模型大小及其 drafters 的 QAT 检查点，旨在优化设备端性能。这为在资源受限环境中部署大型语言模型提供了更高效的方案。
Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama! They reduce memory ...
Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama! They reduce memory requirements while maintaining model quality. E2B: ollama run gemma4:e2b-it-qat E4B: ollama run gemma4:e4b-it-qat 12B: ollama run gemma4:12b-it-qat 26B: ollama run gemma4:26b-a4b-it-qat 31B: ollama run gemma4:31b-it-qat Try them with ollama launch integrations to use with your favorite tools 👇👇👇 Google Gemma @googlegemma We just dropped Gemma 4 Quantization-Aware Training (QAT) checkpoints on Hugging Face! All Gemma 4 model sizes and their drafters are now optimized with QAT to cut memory requirements and maximize on-device performance! 🔗 View Quoted Tweet 💬 1 🔄 4 ❤️ 16 👀 756 📊 3 ⚡