CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gemma / diffusiongemma-26B-A4B-it-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gemmaSubject:

diffusiongemma-26B-A4B-it-4bit

Date: 2026-11-15Commit: a7a8140Signed: 2DC28CC7B26A283B ✓

Image text to text model with 25.8B parameters. Safetensors weights, 16.6 GB in all. Published by mlx-community under Apache-2.0.

25.8B params16.6GBdiffusiongemma-26B-A4B-it-4bitsafetensorspermissive
FactsParams25.8BSize16.6 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/diffusiongemma-26B-A4B-it-4bit
# manifest sha256 0c0c95b381af… · 16.6 GB · 13 files
$ fw verify ./diffusiongemma-26B-A4B-it-4bit mlx-community/diffusiongemma-26B-A4B-it-4bit
From sourceHosted (signed)mlx-community/diffusiongemma-26B-A4B-it-4bitLast check: 2026-11-15 05:03 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of diffusiongemma-26B-A4B-it.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.6 GB
Weights
16.5 GB (safetensors)
Parameters
25.8B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.gemma
Lineage

Original release from the publisher.

Base model: google/diffusiongemma-26B-A4B-it

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:03 UTCpassed

Model card

From the publisher at commit a7a8140. Shown as plain text with links; images open at the publisher.

mlx-community/diffusiongemma-26B-A4B-it-4bit#

This model was converted to MLX format from google/diffusiongemma-26B-A4B-it using mlx-vlm version 0.6.3. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/diffusiongemma-26B-A4B-it-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

13 files · 16.6 GBWeights 16.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md779 Bad3262ee1b00cc856307a469e710991295712fee20480789aa522152785866c8
chat_template.jinja17.3 KB2f1b4d75d067bae3fe44e676721c7f077d243bc007156cb9c2f8b5836613d082
config.json58.9 KBb41320c97651075363f2895e2cbb3d1580670ee11edb653a14290a35bbf7cac5
generation_config.json357 B99334f763c3dbe8b161aeaca1c150a05344299fda2d2e4a0e1d342c744461200
model-00001-of-00004.safetensors5.22 GB4e9e90d11166740e647ab81edc7eb85ce93fbd97bd6a3b352407224b6337833a
model-00002-of-00004.safetensors5.36 GB67508ed60a26b9e725be0fb4c2e5bb8f0b76f02ecd33650c66c3330164257ad2
model-00003-of-00004.safetensors5.37 GBa360651889edf28e7cc50e6d0e30f617b052d8b998cd9b826394f0325cfe9bad
model-00004-of-00004.safetensors602 MBead1033d8d0907f5f7820efb5292a87359ba4683ce9b947fddf5e2e57792ae5f
model.safetensors.index.json165 KB9af3e8635b62d12870e3fe0cc63eafb4bc42d9e031eac409eb5f32cdc974e902
processor_config.json911 Bb113d8d45d04095c078674b92ec5f32b2857abee2c99c6993e1e557affd69cf9
tokenizer.json32.2 MBcc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
tokenizer_config.json2.75 KBc1112569480ce4f86410f29131ff779f8944097f118f5524f4762ca85a32aa5b
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
a7a8140761 pinned now2026-11-15 05:03 UTC13 files · 16.6 GB

Use it

$ fw get mlx-community/diffusiongemma-26B-A4B-it-4bit
# manifest sha256 0c0c95b381af… · 16.6 GB · 13 files
$ fw verify ./diffusiongemma-26B-A4B-it-4bit mlx-community/diffusiongemma-26B-A4B-it-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/diffusiongemma-26B-A4B-it-4bit.json --dir ./diffusiongemma-26B-A4B-it-4bit $ python3 fw.py verify ./diffusiongemma-26B-A4B-it-4bit ./mlx-community__diffusiongemma-26B-A4B-it-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/diffusiongemma-26B-A4B-it-4bit --revision a7a81407613811e8ba63af92ac0d852b809e191f --local-dir ./diffusiongemma-26B-A4B-it-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/diffusiongemma-26B-A4B-it-4bit", revision="a7a81407613811e8ba63af92ac0d852b809e191f") model = AutoModelForImageTextToText.from_pretrained("mlx-community/diffusiongemma-26B-A4B-it-4bit", revision="a7a81407613811e8ba63af92ac0d852b809e191f", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/diffusiongemma-26B-A4B-it-4bit --revision a7a81407613811e8ba63af92ac0d852b809e191f
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
ad3262ee1b00cc856307a469e710991295712fee20480789aa522152785866c8
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gemmaSubject: diffusiongemma-26B-A4B-it-4bitDate: 2026-11-15Commit: a7a8140Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/diffusiongemma-26B-A4B-it-4bit
Pinned commit
a7a81407613811e8ba63af92ac0d852b809e191f
Manifest
diffusiongemma-26B-A4B-it-4bit.json · .minisig
Manifest sha256
0c0c95b381af5cdfb84c9b677ab9972516552ab22d77065bfce0a01dd962b277
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:03 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/diffusiongemma-26B-A4B-it-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/diffusiongemma-26B-A4B-it-4bit.json.minisig $ minisign -Vm diffusiongemma-26B-A4B-it-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

google/diffusiongemma-26B-A4B-it · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/diffusiongemma-26B-A4B-it-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. diffusiongemma-26B-A4B-it-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/diffusiongemma-26B-A4B-it-4bit

Related models

All of alt.freeweights.gemma →
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r128
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r64
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-12B-it-Qwen27-Knowledge-Units-LoRA-r128
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r128
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r64
From: laion <huggingface.co/laion>Subject: Alexandria-Gemma-4-E4B-it-Qwen27-Knowledge-Units-LoRA-r128