What are the hardware requirements for Gemma 4 26B A4B NVFP4?

Gemma 4 26B A4B NVFP4 requires approximately 18.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 26B A4B NVFP4 and how large is it?

Gemma 4 26B A4B NVFP4 is developed by nvidia, a model with 26b 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 Gemma 4 26B A4B NVFP4?

Gemma 4 26B A4B NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 26B A4B NVFP4 by nvidia — VRAM 18.8GB

Name: Gemma 4 26B A4B NVFP4
Author: nvidia

Gemma 4 26B A4B NVFP4 is an open-source language model by nvidia. Features: 26b LLM, VRAM: 18.8GB, License: apache-2.0, LLM Explorer Score: 0.38.

8-bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge... Conversational Gemma4 Gemma4-26b-a4b-it Model optimizer Modelopt Nvfp4 Nvidia Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/Gemma-4-26B-A4B-NVFP4

Gemma 4 26B A4B NVFP4 Parameters and Internals

LLM Name	Gemma 4 26B A4B NVFP4
Repository 🤗	https://huggingface.co/nvidia/Gemma-4-26B-A4B-NVFP4
Base Model(s)	Gemma 4 26B A4B It google/gemma-4-26B-A4B-it
Model Size	26b
Required VRAM	18.8 GB
Updated	2026-08-04
Maintainer	nvidia
Model Type	gemma4
Model Files	10.0 GB: 1-of-2 8.8 GB: 2-of-2
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.6.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 26B A4B 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 Gemma 4 26B A4B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 26B A4B It	0K / 51.6 GB	10405989	1007
Gemma 4 26B A4B	0K / 51.6 GB	624397	370
Gemma 4 26B A4B It	0K / 51.6 GB	28545	28
Gemma 4 26B A4B StyleTune V2	0K / 53.1 GB	1598	49
Gemma 4 26B A4B	0K / 51.6 GB	3368	19
Gemma 4 26B A4b It Bf16	0K / 51.6 GB	1517	3
WaifuGemma4 26B A4b V1	0K / 51.6 GB	850	10
Gemma 4 26B A4B It NVFP4	0K / 16.9 GB	154663	21
Gemma 4 26B A4B It FP8 Dynamic	0K / 28.6 GB	1136349	38
Gemma 4 26B A4B It NVFP4	0K / 16.4 GB	742819	39

Note: green Score (e.g. "73.2") means that the model is better than nvidia/Gemma-4-26B-A4B-NVFP4.