UnslothAI推出75GB内存运行125B模型

精选理由

UnslothAI推出Qwen3.8-Flash模型，性能强劲，内存需求低，是Claude-Opus-4.6（Max）的强劲对手。

AI 摘要

UnslothAI发布Qwen3.8-Flash模型，可在75GB内存上本地运行，性能优于Claude-Opus-4.6（Max），支持CPU RAM/统一内存设置，速度接近VRAM。

原文 · 阿里通义 Qwen

A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day...

A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day-0 support.🥳 Unsloth AI @UnslothAI Qwen3.8-Flash can now be run locally! 🔥 The 125B MoE model outperforms Claude-Opus-4.6 (Max). Run on 75GB RAM via Unsloth GGUFs. Qwen3.8-Flash-Next enables CPU RAM / unified mem setups to deliver near VRAM speeds. Guide: unsloth.ai/docs/models/qw… L GGUF: huggingface.co/unsloth/Qwen3.… j 🔗 View Quoted Tweet 💬 16 🔄 16 ❤️ 242 👀 14526 📊 35 ⚡

Decoder14:40原文

查看原推