First true omni model runs fully in-browser: 280 tok/s with WebGPU
victormustar · x · 2026-10-30
Xenova claims a breakthrough: LFM3-Omni-2B, the first true omni model running 100% locally in a browser, end-to-end with no separate ASR/TTS models. Using custom WebGPU kernels it hits 280 tok/s on an M4 Max, accepting visual, audio, or text input and producing interleaved text and audio tokens — 90 ms to first token, 140 ms to first audio.
More from Infra
- Dell forecasts 200GW AI data center growth by 2030, a $1T opportunity — Beth_Kindig · 2026-10-30
- AI-driven scientific discoveries cost $10M+ compute on Navier-Stokes, $100M+ overall — kimmonismus · 2026-10-30
- Google adds the most compute capacity by 2027 yet trades cheapest among hyperscalers — inductionheads · 2026-10-30
- Swapping 5600X for 5600G slashes Vulkan LLM inference 4x while ROCm stays unaffected — Jebbyk1 · 2026-10-30
- Situational Awareness is raising money for neocloud startup Fluidstack, months after near-collapse — nmasc_ · 2026-10-30
- 16GB GPU bandwidth-per-dollar tier list puts RX 6800 on top — HankYeomans · 2026-10-30