CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gemma / gemma-4-26b-a4b-it-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gemmaSubject:

gemma-4-26b-a4b-it-8bit

Date: 2026-11-14Commit: 33c6d23Signed: 2DC28CC7B26A283B ✓

Image text to text model with 25.8B parameters. Safetensors weights, 28.0 GB in all. Published by mlx-community under Apache-2.0.

25.8B params28.0GBgemma-4-26b-a4b-it-8bitsafetensorspermissive
FactsParams25.8BSize28.0 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/gemma-4-26b-a4b-it-8bit
# manifest sha256 a6f4fb15b870… · 28.0 GB · 15 files
$ fw verify ./gemma-4-26b-a4b-it-8bit mlx-community/gemma-4-26b-a4b-it-8bit
From sourceHosted (signed)mlx-community/gemma-4-26b-a4b-it-8bitLast check: 2026-11-14 21:30 UTC
Run at homeGet help

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

Quantized of gemma-4-26B-A4B-it.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
28.0 GB
Weights
28.0 GB (safetensors)
Parameters
25.8B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
mlx-community
Added
2026-11-14
Section
alt.freeweights.gemma
Lineage

Original release from the publisher.

Base model: google/gemma-4-26B-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.co2026-11-14 21:30 UTCpassed

Model card

From the publisher at commit 33c6d23. Shown as plain text with links; images open at the publisher.

mlx-community/gemma-4-26b-a4b-it-8bit#

This model was converted to MLX format from google/gemma-4-26B-A4B-it at revision 20da991ab4afab98e8f910c4a2e8f4fbefc404ad.

It was generated from the current mlx-vlm source checkout.

Use with mlx-vlm#

pip install -U mlx-vlm
mlx_vlm.generate --model mlx-community/gemma-4-26b-a4b-it-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

15 files · 28.0 GBWeights 28.0 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md753 B7f65a5f0a313b51d75007967515228446e9d9b3b5bb2b52a55a1d1d7b76aa4f5
chat_template.jinja17.5 KB36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0
config.json12.2 KBea476b39447dca4e9361f8f449c2941c2cacd7c80f072b940695407cc54306ad
generation_config.json208 Bd4226bbe3117d2d253ba4609720ba82c6c4ce4627a9a6ae05387c78983ac03de
model-00001-of-00006.safetensors5.18 GBfdf66cb7cec3616751e2162a7581bd9390fd7ab35eb4fbecb749e3b2dcd319f6
model-00002-of-00006.safetensors5.21 GB54ec0f76c9514f2576f908a86923af092dd81d0b8eae44fa2d4919e5a131d4e2
model-00003-of-00006.safetensors5.21 GB8fbffdbdf0a768892a84c8ee5c827f66e131ad40568ba4c202bae9626d627aa9
model-00004-of-00006.safetensors5.21 GBb89800b466a26de4bb4eca33d5970fd6d14255fe6d22feddaf3d1b8d82431df8
model-00005-of-00006.safetensors5.21 GB790699d63d35744aafb4b3dd3da5f33cc0daf759e5800d23e99838a142916082
model-00006-of-00006.safetensors1.95 GB08709a250e4c174b302adab292532f29ab1de6e0ab52567969208be31c5facc8
model.safetensors.index.json177 KB4b96ec862d7ae3f8d150b22b295cefcc9b5ef5e83f172f530dc1f2d2c11339cc
processor_config.json1.32 KBde3e580aebdc98272d4c4547daffe6525fcbae18a83a0e0bcf0d7444d4ee6f37
tokenizer.json32.2 MBcc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
tokenizer_config.json2.74 KB080d9e1aff284e2f6043889cd05367966f7c7b80e025fbc0b06745e218158656
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
33c6d23798 pinned now manifest updated, same commit2026-11-14 21:30 UTC15 files · 28.0 GB
33c6d237982026-11-14 21:30 UTC15 files · 28.0 GB

Use it

$ fw get mlx-community/gemma-4-26b-a4b-it-8bit
# manifest sha256 a6f4fb15b870… · 28.0 GB · 15 files
$ fw verify ./gemma-4-26b-a4b-it-8bit mlx-community/gemma-4-26b-a4b-it-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26b-a4b-it-8bit.json --dir ./gemma-4-26b-a4b-it-8bit $ python3 fw.py verify ./gemma-4-26b-a4b-it-8bit ./mlx-community__gemma-4-26b-a4b-it-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gemma-4-26b-a4b-it-8bit --revision 33c6d23798a0af159529890f79329206dbfbd73c --local-dir ./gemma-4-26b-a4b-it-8bit
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/gemma-4-26b-a4b-it-8bit", revision="33c6d23798a0af159529890f79329206dbfbd73c") model = AutoModelForImageTextToText.from_pretrained("mlx-community/gemma-4-26b-a4b-it-8bit", revision="33c6d23798a0af159529890f79329206dbfbd73c", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gemma-4-26b-a4b-it-8bit --revision 33c6d23798a0af159529890f79329206dbfbd73c
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. 2026-11-14
Text in
README.md
Text sha256
7f65a5f0a313b51d75007967515228446e9d9b3b5bb2b52a55a1d1d7b76aa4f5
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: gemma-4-26b-a4b-it-8bitDate: 2026-11-14Commit: 33c6d23Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/gemma-4-26b-a4b-it-8bit
Pinned commit
33c6d23798a0af159529890f79329206dbfbd73c
Manifest
gemma-4-26b-a4b-it-8bit.json · .minisig
Manifest sha256
a6f4fb15b8708a85cb76f5cb7474613bfb7ce0bf5cecb099578cca54cc624b5c
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26b-a4b-it-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26b-a4b-it-8bit.json.minisig $ minisign -Vm gemma-4-26b-a4b-it-8bit.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/gemma-4-26B-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/gemma-4-26b-a4b-it-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. gemma-4-26b-a4b-it-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/gemma-4-26b-a4b-it-8bit

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