Skip to content
Local AI Wizard
Your machine
Theme

diffusiongemma-26B-A4B-it

Google · google/diffusiongemma-26B-A4B-it

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher15 resultsGoogle's model card · read 2026-10-25 · not ranked · see them
Memory needed~20 GBQ4 weights + working room, before the machine's reserve
Parameters25.8 BHub safetensors total
Repository updated2026-07-15A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

15 results · Google's model card · read 2026-10-25
MMLU Pro
77.6%
AIME 2026 no tools
69.1%
LiveCodeBench v6
69.1%
Codeforces ELO
1,429
GPQA Diamond
73.2%
Tau2 (average over 3)
56.2%
HLE no tools
11.0%
HLE with search
11.9%
Every reported result15
BigBench Extra Hard
47.6%
MMMLU
81.5%
MMMU Pro
54.3%Vision
OmniDocBench 1.5 (average edit distance, lower is better)
0.319Vision
MATH-Vision
70.5%Vision
MedXPertQA MM
49.0%Vision
MRCR v2 8 needle 128k (average)
32.0%Long Context

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results); column “DiffusionGemma 26B A4B”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 48

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 48

Within memory, outside the fast part 45

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 45

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

Google released diffusiongemma-26B-A4B-it on 2026-06-10: a vision-language model that answers about images, with 25.8B parameters on the Hugging Face count and the Apache 2.0 license.

Check first

License: commercial use allowed. At Q4 the weights load about 19.3 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install -U transformers torch accelerate
Transformers · model card · Getting Started
from transformers import DiffusionGemmaForBlockDiffusion, AutoProcessor

MODEL_ID = "google/diffusiongemma-26B-A4B-it"

# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = DiffusionGemmaForBlockDiffusion.from_pretrained(
    MODEL_ID,
    dtype="auto",
    device_map="auto",
)
Transformers · model card · Getting Started
# Prompt
message = [
    {"role": "user", "content": "Why is the sky blue?"}
]

# Process input
input_ids = processor.apply_chat_template(
    message,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)
output = model.generate(**input_ids, max_new_tokens=512)

# Parse output
text = processor.decode(output[0], skip_special_tokens=False)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
image-text-to-text
Architecture
DiffusionGemmaForBlockDiffusion
Library in source
transformers
Weight license
Apache 2.0google/diffusiongemma-26B-A4B-it model card (Hugging Face: "License: Apache 2.0") · read 2026-10-19source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Released
Introducing DiffusionGemma (publisher announcement; meta article:published_time) · read 2026-10-19source
Every stored field11 fields
Revision checked
f7f5b7f5fa82ffc52addd066915886d497f5517b
Architecture
DiffusionGemmaForBlockDiffusion
Library
transformers
Hub task tag
image-text-to-text
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-06-09creation is not the model's release
Repository updated
2026-07-15a commit is not a release date
Hub downloads (30 days) · likes
633,036 · 1,312this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-19. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.