Skip to content
Weights Not Walls
Menu

google

diffusiongemma-26B-A4B-it

Reviewedaccepts images
Size
25.8B parameters, 4.0B active (from the repo name)counted from the safetensors header on the Hub
Licence
custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
9 Jun 2026the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)DiffusionGemmaForBlockDiffusion
On Hugging Face
google/diffusiongemma-26B-A4B-it599k downloads in the last 30 days, 1.3k likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.35 GB, worked out from the model's config (google/diffusiongemma-26B-A4B-it), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

unsloth/diffusiongemma-26B-A4B-it-GGUF (converted by unsloth), 19k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q4_K_M15.7 GBfile size16.5 GB15.7 + 0.35 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
Ollama
ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
Download
hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q4_K_M.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF
Q5_K_M17.8 GBfile size18.7 GB17.8 + 0.35 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q5_K_M
Ollama
ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q5_K_M
Download
hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q5_K_M.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF
Q6_K21.1 GBfile size22.0 GB21.1 + 0.35 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q6_K
Ollama
ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q6_K
Download
hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q6_K.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF
Q8_025.0 GBfile size25.9 GB25.0 + 0.35 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:Q8_0
Ollama
ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q8_0
Download
hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-Q8_0.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF
BF1647.1 GBfile size47.9 GB47.1 + 0.35 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16
Ollama
ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16
Download
hf download unsloth/diffusiongemma-26B-A4B-it-GGUF --include "diffusiongemma-26B-A4B-it-BF16.gguf" --local-dir diffusiongemma-26B-A4B-it-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/diffusiongemma-26B-A4B-it-4bit15.4 GBfile size16.3 GB15.4 + 0.35 + 0.50Download page
MLX 4bitmlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit16.6 GBfile size17.4 GB16.6 + 0.35 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights48.1 GBfile size49.0 GB48.1 + 0.35 + 0.50
hf download google/diffusiongemma-26B-A4B-it --local-dir diffusiongemma-26B-A4B-it
Other conversions (11; sizes not read)

The Hub tags 37 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.