Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · zelk12

MT-Gen1-gemma-3-12B

MT-Gen1-gemma-3-12B is a 12.19B-parameter Gemma-3 merge from zelk12. According to the model card, it uses DARE TIES mergekit on an amoral Gemma-3 base.

Publisher
zelk12
Task
image-text-to-text
Model type
gemma3
License
gemma
Library
transformers
Publication status
Accepted · not indexed

Model overview

MT-Gen1-gemma-3-12B is published by zelk12 as a Transformers image-text-to-text model. The captured configuration identifies Gemma3ForConditionalGeneration and Safetensors metadata reports 12187325040 parameters. According to the model card, it is a mergekit DARE TIES merge on soob3123/amoral-gemma3-12B-v2, with card data recording gemma.

Recorded capabilities

DARE TIES mergekit merge

According to the model card, this is a mergekit merge made with DARE TIES on soob3123/amoral-gemma3-12B-v2 as base.

Five-model Gemma-3 mix

According to the model card, the merge combines Fallen, Omega-Directive, saiga, amoral QAT, and amoral base variants with density 0.5 and weight 0.5.

Gemma 3 architecture and size

Captured config reports Gemma3ForConditionalGeneration and gemma3, with Safetensors metadata reporting about 12.19B parameters.

bfloat16 normalized config

According to the model card, the merge configuration used normalize true with bfloat16 dtype.

Use cases in the source record

  • Text and image-grounded generation experiments where the record is typed image-text-to-text and described as a Gemma-3 merge.
  • Merge-behavior comparison across the five listed Gemma-3-12B contributors using the publisher YAML configuration.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Merge behavior claims come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: zelk12/MT-Gen1-gemma-3-12B

Captured: Unknown. Processed: 2026-09-07T19:35:33.216894+00:00.

merge This is a merge of pre-trained language models created using mergekit . Merge Details Merge Method This model was merged using the DARE TIES merge method using soob3123/amoral-gemma3-12B-v2 as a base. Models Merged The following models were included in the merge: TheDrummer/Fallen-Gemma3-12B-v1 ReadyArt/The-Omega-Directive-Gemma3-12B-v1.0 IlyaGusev/saiga_gemma3_12b huihui-ai/gemma-3-12b-it-abliterated soob3123/amoral-gemma3-12B-v2-qat Configuration The following YAML configuration was used to produce this model: models: - model: soob3123/amoral-gemma3-12B-v2 #no parameters necessary for base model - model: IlyaGusev/saiga_gemm…

F001F002F003F004F005F006F007F010F011F012F013