What are the hardware requirements for Phonellm Max Alpha 2?

Phonellm Max Alpha 2 requires approximately 188.5 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phonellm Max Alpha 2 and how large is it?

Phonellm Max Alpha 2 is developed by pipecat-ai, a model with 120b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phonellm Max Alpha 2?

Phonellm Max Alpha 2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phonellm Max Alpha 2 by pipecat-ai — VRAM 188.5GB, 1024K context

Name: Phonellm Max Alpha 2
Author: pipecat-ai

Phonellm Max Alpha 2 is an open-source language model by pipecat-ai. Features: 120b LLM, VRAM: 188.5GB, Context: 1024K, License: other, LLM Explorer Score: 0.34.

Base model:finetune:nvidia/nvi... Base model:nvidia/nvidia-nemot... Conversational En Endpoints compatible Function-calling Mixture-of-experts Nemotron Nemotron h Phone Pipecat Region:us Safetensors Sharded Tensorflow Tool-use Voice-agent

Model Card on HF 🤗: https://huggingface.co/pipecat-ai/phonellm-max-alpha-2

Phonellm Max Alpha 2 Parameters and Internals

LLM Name	Phonellm Max Alpha 2
Repository 🤗	https://huggingface.co/pipecat-ai/phonellm-max-alpha-2
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Model Size	120b
Required VRAM	188.5 GB
Updated	2026-10-20
Maintainer	pipecat-ai
Model Type	nemotron_h
Model Files	4.3 GB: 1-of-58 4.3 GB: 2-of-58 4.3 GB: 3-of-58 4.3 GB: 4-of-58 4.3 GB: 5-of-58 4.3 GB: 6-of-58 4.3 GB: 7-of-58 4.3 GB: 8-of-58 4.3 GB: 9-of-58 4.3 GB: 10-of-58 4.3 GB: 11-of-58 4.3 GB: 12-of-58 4.3 GB: 13-of-58 4.3 GB: 14-of-58 4.3 GB: 15-of-58 4.3 GB: 16-of-58 4.2 GB: 17-of-58 4.3 GB: 18-of-58 4.3 GB: 19-of-58 4.3 GB: 20-of-58 4.3 GB: 21-of-58 4.3 GB: 22-of-58 4.3 GB: 23-of-58 4.1 GB: 24-of-58 4.3 GB: 25-of-58 4.3 GB: 26-of-58 4.3 GB: 27-of-58 4.3 GB: 28-of-58 4.3 GB: 29-of-58 4.3 GB: 30-of-58 4.1 GB: 31-of-58 4.3 GB: 32-of-58 4.3 GB: 33-of-58 4.3 GB: 34-of-58 4.3 GB: 35-of-58 4.3 GB: 36-of-58 4.3 GB: 37-of-58 4.1 GB: 38-of-58 4.3 GB: 39-of-58 4.3 GB: 40-of-58 4.3 GB: 41-of-58 4.3 GB: 42-of-58 4.3 GB: 43-of-58 4.3 GB: 44-of-58
Supported Languages	en
Model Architecture	NemotronHForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.8.1
Vocabulary Size	131072

Rank the Phonellm Max Alpha 2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Phonellm Max Alpha 2

Best Alternatives	Context / RAM	Downloads	Likes
... Nemotron 3.5 Super VL Finance	1024K / 172 GB	2062	11
...motron 3.5 Super VL Healthcare	1024K / 172 GB	2011	10
...on 3 Super 120B A12B Base BF16	1024K / 209.5 GB	13053	32
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	3041935	408
...emotron 3 Super 120B A12B BF16	256K / 194.6 GB	864394	414
...motron 3 Super 120B A12B NVFP4	256K / 80.3 GB	1132	27
...DIA Nemotron 3 Super 120B A12B	256K / 214.5 GB	294	3
...Nemotron 3 Super 120B A12B FP8	256K / 128.4 GB	81	10
...Nemotron 3 Super 120B A12B FP8	256K / 128.4 GB	221272	269
Nemotron 3 Hummingbird	256K / 49 GB	48	2

Note: green Score (e.g. "73.2") means that the model is better than pipecat-ai/phonellm-max-alpha-2.