PhoneLLM
by Pipecat · Model · Language & code models
Fine-tune of Nemotron 3 Nano (30B, 3.5B active) for phone voice agents, open weights, no thinking, temperature 0
AccessOpen weightsNeeds~74 GBSize30B parametersLicenseBSD-2-Clause plus NVIDIA Nemotron Open Model License
Evidence
- Aug 30In a three-tool test with a rejected slot and mid-sentence party-size change, it called check availability with four, in about a second
- Aug 30Claimed to match or beat GPT-5.6 Terra and Gemini 3.6 Flash on PhoneBench, 5-10x faster to first token at a fraction of the cost
- Aug 30Shown calling create_reservation where base Nemotron 3 Nano only talks and never books the table