---
format: "aidr-story-markdown/v1"
id: "630214ef03cbaf0aa70c1ae954783d6eaffc3aa39610a78df6e8ee82e13e4941"
canonical_url: "https://aidr.today/630214ef?lang=en"
title: "PhoneLLM Debuts Open Voice AI Models With Sub-100ms Latency"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-15T22:39:01.000Z"
category: "Open Source"
topics: ["nvidia","llm","open-source"]
source_urls: ["https://marketbrief.now/ai/phonellm-debuts-open-voice-ai-models-with-sub-100ms-latency-ff609474","https://huggingnews.com/ai/phonellm-debuts-open-voice-ai-models-with-sub-100ms-latency-ff609474"]
summary: "PhoneLLM has launched two open voice AI models, PhoneLLM Mini (30B parameters) and PhoneLLM Max (120B parameters), offering sub-100ms and sub-200ms latency respectively, available through AWS, Baseten, Modal, and Cloudflare Workers AI."
---

# PhoneLLM Debuts Open Voice AI Models With Sub\-100ms Latency

> [Open the canonical story](<https://aidr.today/630214ef?lang=en>)

**Published:** 2026-10-15T22:39:01.000Z
**Category:** Open Source
**Topics:** nvidia, llm, open\-source

## Summary

PhoneLLM has launched two open voice AI models, PhoneLLM Mini \(30B parameters\) and PhoneLLM Max \(120B parameters\), offering sub\-100ms and sub\-200ms latency respectively, available through AWS, Baseten, Modal, and Cloudflare Workers AI\.

## Sources

- [Story source](<https://marketbrief.now/ai/phonellm-debuts-open-voice-ai-models-with-sub-100ms-latency-ff609474>)
- [Story source](<https://huggingnews.com/ai/phonellm-debuts-open-voice-ai-models-with-sub-100ms-latency-ff609474>)