VLS-Local-LLM-Server
Run any GGUF model locally with up to 32M tokens of context. OpenAI-compatible, no cloud, no retraining. Windows and Linux, one command each.
原文来源AI 开源 Releases
查看官方原文
Run any GGUF model locally with up to 32M tokens of context. OpenAI-compatible, no cloud, no retraining. Windows and Linux, one command each.