Aiqre

Model library / pipecat-ai

phonellm-alpha-1

PhoneLLM Alpha 1 is an open-weights MoE language model fine-tuned for low-latency voice agent applications.

31.6B

6 of 128 experts active per token

262,144

Context length in tokens, as published

59 GiB

Weights at the released precision

bsd-2-clause

Licence declared on the repository

Overview

What this model is.

PhoneLLM Alpha 1 is a 31.6 billion-parameter mixture-of-experts language model based on Nemotron 3 Nano, released by pipecat-ai. The publisher describes it as an open-weights model fine-tuned for low-latency, multi-turn voice agent workloads such as customer-service calls in finance, healthcare, retail, hospitality and insurance sectors overall.

The model contains 31.6 B parameters, stored in bfloat16, and uses 128 experts with six active per token. It supports a 262 k token context window and is licensed under BSD-2-Clause, allowing unrestricted commercial use. Deployment requires hardware capable of MoE inference; the official NVFP4 checkpoint targets NVIDIA Blackwell GPUs with BF16 KV cache.

Specification

The published shape.

Repositorypipecat-ai/phonellm-alpha-1
Publisherpipecat-ai
Published24 August 2026
ArchitectureNemotronHForCausalLM
Model typenemotron_h
Parameters31,577,937,344
Experts128 total, 6 active per token
Layers52
Hidden size2,688
Attention heads32, 2 key/value heads
Context length262,144 tokens
Vocabulary131,072 tokens
Weight formatbfloat16
Licencebsd-2-clause
Base modelnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf1658.8 GiBFull precision as released
fp829.4 GiB8-bit, near-lossless on most models
int414.7 GiB4-bit, smallest footprint

The cache costs 52 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 13.0 GiB. Concurrency multiplies that number, not the weights.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB 4 17.6 GiB the full 262,144 tokens
RTX 5090 32GB 4 46.4 GiB the full 262,144 tokens
L40S 48GB 2 22.6 GiB the full 262,144 tokens
A100 80GB 1 10.7 GiB about 215,391 tokens
H100 80GB 1 10.7 GiB about 215,391 tokens
RTX PRO 6000 96GB 1 25.1 GiB the full 262,144 tokens
H200 141GB 1 65.6 GiB the full 262,144 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve pipecat-ai/phonellm-alpha-1 \
  --max-model-len 262144 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does phonellm-alpha-1 need?

The weights take about 59 GiB at the released precision. That fits on one A100 80GB, which leaves roughly 11 GiB for the key-value cache.

What licence does phonellm-alpha-1 use?

The repository declares bsd-2-clause. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2

Pantheon-Reasoning-26B-A4B-1.1-V2 is a 26.5 billion-parameter Gemma-4 mixture-of-experts finetune aimed at role-play scenarios, i…

nex-agi/Nex-N2.5-mini

Nex-N2.5-mini is a 35.1 billion-parameter mixture-of-experts language model released under Apache-2.0.

inclusionAI/LLaDA2.2-mini

LLaDA2.2-mini is a 16.3 billion-parameter MoE diffusion language model with 128 k token context, supporting Levenshtein editing.

IFM/K2-Horizon-32B

K2-Horizon-32B-Stage1 is a 32-billion-parameter dense decoder-only model released by IFM for benchmarking agentic, coding and rea…

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.