Inco AI (@inco

Pinned

Splash 1.3.0 is out, and it's about the wait before your local agent starts answering ⚡ If you switch projects and come back, SSD offloading brings the first token down from 19 seconds to 1. New tasks start 1.5× faster, thanks to the Neural Engine. All on a 24 GB M6 Mac.

00:00

Kick off #SFTechWeek with Inco AI + TokenRouter at our Token Happy Hour! 🍸 📅 Oct 5, 4:30–7pm 📍 Industrious, Palo Alto Come talk AI over batched cocktails + bites. RSVP:

Token Happy Hour-#SFTechWeek | Partiful

31× more video per GPU, at 1/15 the cost ⚡ That's @linewiseAI's video agent on Inco vs. their own pipeline. The agent is thorough. Before it calls a moment idle, it checks what came before and after, reads the sensors, and zooms in. Lots of model calls, and we make them fast.

linewise

@linewiseAI

30 Sept

One week of our video data: 16,190 hours. A full-time worker would need 8 years to watch it. Our agent-native infra analyzes it in a day, with inference on @inco_ai: 31× the throughput per GPU at 1/15 the cost per hour of video.

00:00

Inco AI

@inco_ai

24 Sept

DFlash drafts a whole block in parallel. DFlash 2 picks one path through the block instead of the top token at each position: over 20% more tokens per pass, about 1% more latency. Our co-founder and chief scientist @zhijianliu explains how at @modal Runtime in SF on Oct 1.

Zhijian Liu

@zhijianliu

23 Sept

DFlash: Keep Drafting Parallel My talk at @modal Runtime in SF on Oct 1. The drafter was the serial bottleneck, so DFlash made it parallel. That moved the bottleneck to selection, so DFlash 2 fixed that.

00:00

Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro ⚡ Meet Inco Splash: our open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents.

00:00

192