What are the hardware requirements for Ising Calibration 1.5 31B NVFP4?

Ising Calibration 1.5 31B NVFP4 requires approximately 20.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ising Calibration 1.5 31B NVFP4 and how large is it?

Ising Calibration 1.5 31B NVFP4 is developed by nvidia, a model with 31b 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 Ising Calibration 1.5 31B NVFP4?

Ising Calibration 1.5 31B NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ising Calibration 1.5 31B NVFP4 by nvidia — VRAM 20.5GB

Name: Ising Calibration 1.5 31B NVFP4
Author: nvidia

Ising Calibration 1.5 31B NVFP4 is an open-source language model by nvidia. Features: 31b LLM, VRAM: 20.5GB, License: other, LLM Explorer Score: 0.29.

Arxiv:2604.25884 Calibration Conversational Endpoints compatible Gemma4 Image-text-to-text Ising calibration Modelopt Nvfp4 Nvidia Quantum Region:us Safetensors Sharded Tensorflow Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/nvidia/Ising-Calibration-1.5-31B-NVFP4

Ising Calibration 1.5 31B NVFP4 Parameters and Internals

LLM Name	Ising Calibration 1.5 31B NVFP4
Repository 🤗	https://huggingface.co/nvidia/Ising-Calibration-1.5-31B-NVFP4
Base Model(s)	google/gemma-4-31b google/gemma-4-31b
Model Size	31b
Required VRAM	20.5 GB
Updated	2026-08-08
Maintainer	nvidia
Model Type	gemma4
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 0.5 GB: 3-of-3
Model Architecture	Gemma4ForConditionalGeneration
License	other
Transformers Version	5.6.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Ising Calibration 1.5 31B NVFP4 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 Ising Calibration 1.5 31B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 31B It	0K / 62.6 GB	10706625	2780
Gemma 4 31B It	0K / 62.6 GB	30339	22
Gemma 4 31B IT NVFP4	0K / 32.6 GB	2773900	547
Gemma 4 31B It Scotoma 2	0K / 62.5 GB	221	38
Gemma 4 31B It Abliterated	0K / 62.5 GB	751355	24
Gemma 4 31B StyleTune	0K / 65.4 GB	2305	82
Gemma 4 Novelist Eclipse 31B	0K / 62.6 GB	929	30
Gemma 4 31B It Heretic	0K / 62.5 GB	5541	63
Pantheon Reasoning 31B 1.1	0K / 65.4 GB	294	20
Equinox 31B	0K / 62.6 GB	275	59

Note: green Score (e.g. "73.2") means that the model is better than nvidia/Ising-Calibration-1.5-31B-NVFP4.