CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gemma / gemma-3-12b-it
From: google <huggingface.co/google>Newsgroups: alt.freeweights.gemmaSubject:

gemma-3-12b-it

Date: 2026-11-15

Image text to text model with 12.2B parameters. Safetensors weights, 24.4 GB in all. Published by google under Gemma (custom).

12.2B params24.4GBgemma-3-12b-itsafetensorsgated
FactsParams12.2BSize24.4 GBFormatssafetensorsTaskimage text to textLicenseGemma (custom)From the publisher · Gatedgatedread terms
$ fw info google/gemma-3-12b-it
link only — read the license:
https://huggingface.co/google/gemma-3-12b-it
From the publisher · Gatedgoogle/gemma-3-12b-it
Get help

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

Fine-tune of gemma-3-12b-pt.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
24.4 GB
Weights
see files
Parameters
12.2B
Formats
safetensors
Task
image text to text
License
Gemma (custom) (gated)
Files
link only
Publisher
google
Added
2026-11-15
Section
alt.freeweights.gemma
Lineage

Original release from the publisher.

Base model: google/gemma-3-12b-pt

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

Model card

No model card stored here.This model is listed with a link to the publisher. Read the publisher's page: https://huggingface.co/google/gemma-3-12b-it

Files

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

There is no manifest and no file list for a link-only model.

Use it

$ fw info google/gemma-3-12b-it
link only — read the license:
https://huggingface.co/google/gemma-3-12b-it
Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

Read the license Open the source

License

Name
Gemma (custom)
Id
LicenseRef-Gemma
Class
Gated
Redistribution
click-through
Listing
From the publisher
Decided
License as declared by the publisher. No person read it. 2026-11-15
Terms gate
Yes. The commands stay folded until you open them after reading the license.

Read the license text

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

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

Provenance

From: google <huggingface.co/google>Newsgroups: alt.freeweights.gemmaSubject: gemma-3-12b-itDate: 2026-11-15
Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.
Source
huggingface.co/google/gemma-3-12b-it
Manifest
None: Freeweights does not pin or sign link-only models.
Takedowns
None.

Model tree

Parent

google/gemma-3-12b-pt · this model is a finetune of it

11 models in the catalog name this one as their parent.

Fine-tunes
3
Quantizations
8
Fine-tunes 3
Quantizations 8
Get it
License and source
Source
huggingface.co/google/gemma-3-12b-it

Variants

8 quantized or adapter builds of gemma-3-12b-it. Each has its own license check and page.

SubjectSizeParamsLicenseDate
gemma-3-12b-it-GGUFFrom the publisher From: unsloth in alt.freeweights.gemma200 GB—Gated2026-11-15google_gemma-3-12b-it-GGUFFrom the publisher From: bartowski in alt.freeweights.gemma192 GB—Gated2026-11-15gemma-3-12b-it-GGUFFrom the publisher From: ggml-org in alt.freeweights.gemma44.2 GB—Gated2026-11-15gemma-3-12b-it-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.gemma36.8 GB—Gated2026-11-15gemma-3-12b-it-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.gemma7.84 GB12.5BGated2026-11-15gemma-3-12b-it-unsloth-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.gemma12.8 GB12.4BGated2026-11-15gemma-3-12B-it-qat-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.gemma7.74 GB—Gated2026-11-15gemma-3-12b-it-qat-q4_0-ggufFrom the publisher From: google in alt.freeweights.gemma8.93 GB—Gated2026-11-15

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