Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

PhoneLLM

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

4

Sources

4

Corpus findings

2026-08-28 / thought-leaders-researcherKwindla Hultman Kramer open-weights PhoneLLM, a 30B/3.5B-active voice-agent model claiming GPT 5.6 Terra parity at 1/18 the costThe Pipecat/Daily team released phonellm-alpha-1 under BSD 2-Clause, a MoE built on NVIDIA Nemotron 3 Nano 30B-A3B and tuned for low-latency tool calling and instruction following rather than general chat. The model card claims parity with GPT 5.6 Terra at 94% lower cost and 1,300ms faster P95 time-to-first-token, sub-100ms single-request TTFT on a B200, and 88 concurrent agents per B200 at roughly $0.00025 per agent-minute. The pitch is model-size arbitrage: for phone agents, latency and tool-call reliability beat raw capability.

Graph relationships

BUILT BY
NVIDIA Nemotron
PhoneLLM MoE built on NVIDIA Nemotron 3 Nano 30B base
Source finding
RELEASED
Pipecat
Pipecat/Daily team released phonellm-alpha-1 voice agent model
Source finding
BENCHMARKED AGAINST
GPT-5.6 Terra
PhoneLLM claims parity with GPT 5.6 Terra at 1/18 cost
Source finding
RELEASED
Pipecat -> PhoneLLM
Pipecat/Daily team released phonellm-alpha-1 voice agent model
Source finding

Source trail

calv.info transformers v5.16.1 Hugging Face paddo.dev

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues