Introducing PhoneLLM, an open model for voice agents.
GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost.
For voice agents, we need models that are both very low latency and very good at tool calling and instruction following.
There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem.
For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model.
But if you need your agent to respond at voice conversation speed, you can't use thinking models.
PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled.
The results are really good: accurate tool calling and concise, on-topic responses in long conversations.
And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-)
But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines.
You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today.
More details about this model, including weights on @huggingface, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...
🏐 Başarı Hikayesi 🌟
"Sportio ile hayatımız kolaylaştı! 👏
Velilerle iletişimden, yoklama ve aidat takibine kadar tüm kulüp yönetimini tek uygulamada yapıyoruz. Artık işlerimiz çok daha pratik! 🎯✨"
- Fatma Ercan
Voleybol Şube Sorumlusu
Instagram: @bereketlisporvoleybol 🏆
Siz de Sportio ailesine katılın! ⭐️
#Sportio #Voleybol #SporKulübü #SporYönetimi #SporOkul
Korkuyor musunuz?
Bitcoin Ne olacak?
Bu hafta itibariyle piyasalarda bizleri neler bekliyor?
En kötüsü geride kaldı mı?
Hepsini konuşacağız!
Canlı yayınımız başladı!
https://t.co/okkFCFVBSY
🔔 https://t.co/GbIsYBbbGy Whitelist is now LIVE! 🔔
A compendium of trading tools for multiple ecosystems - all in one app 📈
📌 Whitelist Here - https://t.co/kfmlPMr3dC
🔗 IDO Guidelines - https://t.co/BMwXxMWwZW
Kripto trading özellikle price action konsepti ile ilgili uzun süredir biriktirdiğim geneli türkçe olan linkleri flood olarak ileteceğim. Bunları sindirip bol backtest yaptığınızda donanım olarak trading e hazır olacaksınız. Başlayalım 🧵
I just entered @AutoTrader_UK’s monthly️ #ElectricCarGiveaway & you can too! This month’s prize is a Tesla Model 3, worth over £44k! All information (including Ts&Cs) can be found here: https://t.co/oRuPM4j22B
Blasting off Solanium's NFT season with @FlippiesNFT
➡️ Register for the whitelist:
https://t.co/A8VM9nQRPk
ℹ️ Read more about the launch process:
https://t.co/ouodIyiSbU
🐧 Check out the collection:
https://t.co/QVhJ7X2gnG
LFG!
#Solana#SolanaSummer#Solanium $SLIM
çorlu tren faciasının bilirkişi heyetinde yeralan prof. dr. mustafa karaşahin 17 temmuz’da kazanın sebebinin aşırı yağış olduğunu söylüyor ve 25 insanın ölümüne neden olan menfez için “başarılı bir menfez” diyor. kim bu bilirkişi. önce konuşmasını izleyelim kim olduğunu yazacağım