kwindla @kwindla · 01 Sep 2026
I joined the Pipecat TV crew to talk about PhoneLLM: a super low-latency LLM trained on voice agent scenarios. We talked about building agents with a small-ish LLM like this, compared to using a big model. PhoneLLM is based on Nemotron 3 Nano, so it's a 30B-A3B MoE. Prompting a https://t.co/mq0FZ7QifS
3 711Views
65Likes
4Reposts
8Replies
0Quotes
46Bookmarks
Is that a lot?
0.72×vs this author's median5 148 views is typical
31Percentile for this authorof 13 recent posts
2.41×vs 10K–100K median1 540 views is typical
23.59%Reachviews ÷ followers
2.08%Engagement rateof viewers reacted