IT之家 · 智能时代 · 10/6/2026, 7:45:52 AM
Strata Engine Lets 12GB GPUs Run 125B Qwen3.8 Model
By IT之家Original title: 12GB 显存显卡跑 125B Qwen3.8 模型：Strata 登场，单张 RTX 5070 跑出 94 词元 / 秒
68AI Score
Executive Summary
Developer Niko1221 has open-sourced the Strata inference engine, enabling quantized Qwen3.8-Flash-Next (125B parameters) to run on consumer GPUs with 12GB+ VRAM, such as the RTX 5070. The solution achieves a generation speed of 94 tokens per second, demonstrating efficient deployment of large models on low-memory hardware.
SOURCE COVERAGEOriginal coverage
科技媒体 gigazine 今天（10 月 6 日）报道，报道称开发者 Niko1221 开源推出 Strata 引擎，可以在 12GB 及以上显存的消费级显卡上，运行量化的 Qwen3.8-Flash-Next 模型（1250 亿参数）。