Cohere 把最强模型做到 W4A4 量化还开源了，做推理部署的团队可以直接拿来降成本，值得一试。
Cohere 发布了其最强开源大模型 Command A+，并已在 Hugging Face 上提供 W4A4 量化版本。该量化技术能在几乎不损失性能的情况下大幅降低模型部署的硬件需求，显著减少服务占用空间。开发者可以直接下载使用，适合资源受限的部署场景。
Command A+ is available on @huggingface with W4A4 quantization 🤗 Cut your serving footprint dramat...
Command A+ is available on @huggingface with W4A4 quantization 🤗 Cut your serving footprint dramatically with virtually zero performance degradation. Try it now: huggingface.co/CohereLabs/com… 1 Cohere @cohere Introducing: Cohere Command A+ We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 8 🔄 15 ❤️ 118 👀 23384 📊 20 ⚡