What are the hardware requirements for Diffusiongemma 26B A4B It Int4 AutoRound?

Diffusiongemma 26B A4B It Int4 AutoRound requires approximately 29.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Diffusiongemma 26B A4B It Int4 AutoRound and how large is it?

Diffusiongemma 26B A4B It Int4 AutoRound is developed by Intel, 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 Diffusiongemma 26B A4B It Int4 AutoRound?

Diffusiongemma 26B A4B It Int4 AutoRound is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Diffusiongemma 26B A4B It Int4 AutoRound by Intel — VRAM 29.3GB

Name: Diffusiongemma 26B A4B It Int4 AutoRound
Author: Intel

Diffusiongemma 26B A4B It Int4 AutoRound is an open-source language model by Intel. Features: 26b LLM, VRAM: 29.3GB, LLM Explorer Score: 0.31.

Arxiv:2309.05516 4-bit Auto-round Base model:google/diffusiongem... Base model:quantized:google/di... Conversational Diffusion gemma Image-text-to-text Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Intel/diffusiongemma-26B-A4B-it-int4-AutoRound

Diffusiongemma 26B A4B It Int4 AutoRound Parameters and Internals

LLM Name	Diffusiongemma 26B A4B It Int4 AutoRound
Repository 🤗	https://huggingface.co/Intel/diffusiongemma-26B-A4B-it-int4-AutoRound
Base Model(s)	Diffusiongemma 26B A4B It google/diffusiongemma-26B-A4B-it
Model Size	26b
Required VRAM	29.3 GB
Updated	2026-08-10
Maintainer	Intel
Model Type	diffusion_gemma
Model Files	5.4 GB: 1-of-6 5.4 GB: 2-of-6 5.4 GB: 3-of-6 5.4 GB: 4-of-6 5.0 GB: 5-of-6 2.7 GB: 6-of-6 1.5 GB
Model Architecture	DiffusionGemmaForBlockDiffusion
Transformers Version	5.11.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Diffusiongemma 26B A4B It Int4 AutoRound 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 Diffusiongemma 26B A4B It Int4 AutoRound

Best Alternatives	Context / RAM	Downloads	Likes
Diffusiongemma 26B A4B It	0K / 51.6 GB	1899472	1167
...iffusiongemma 26B A4B It NVFP4	0K / 18.8 GB	1881298	107
...iffusiongemma 26B A4B It NVFP4	0K / 18.1 GB	241109	19
Diffusiongemma 26B A4B It	0K / 51.6 GB	10205	6
...Gemma 26B E38 Abliterated BF16	0K / 51.6 GB	39	0
...iffusiongemma 26B A4B It Mxfp4	0K / 14.8 GB	616	6
Diffusiongemma 26B A4B It	0K / 51.6 GB	48	1
...iffusiongemma 26B A4B It Nvfp4	0K / 15.6 GB	242	5
...iffusiongemma 26B A4B It Mxfp8	0K / 27.3 GB	210	3
Diffusiongemma 26B A4B It Bf16	0K / 51.6 GB	185	2

Note: green Score (e.g. "73.2") means that the model is better than Intel/diffusiongemma-26B-A4B-it-int4-AutoRound.