xenovacom· @xenovacom · X·· 1 天前AI 评分
Hugging Face 发布 LFM3-Omni-2B，实现浏览器内全端到端多模态运行
Hugging Face 发布 LFM3-Omni-2B，可在浏览器内 100% 本地端到端运行，无需单独的 ASR 或 TTS 模型。该模型通过自定义 WebGPU kernels，在 M4 Max 上以约 280 tok/s 运行，可接收视觉、音频或文本输入，并交错生成文本与音频 token，首个 token 延迟为 90 ms，首个音频延迟为 140 ms。
We've just made a breakthrough: the first true omni model running 100% locally in a browser... fully end-to-end, with no separate ASR or TTS models needed.
With custom WebGPU kernels, we're able to run LFM3-Omni-2B at ~280 tok/s on my M4 Max, accepting visual, audio, or text and producing interleaved text and audio tokens. Just 90 ms to the first token and 140 ms to the first audio.
The future of on-device multimodal AI agents is going to be wild.
来源：xenovacom · x.com