12.19B Gemma 3 scale
Captured config identifies Gemma3ForConditionalGeneration and Safetensors metadata reports 12187325040 parameters.
Open Source Model Profile · zelk12
MT-Gen4_gemma-3-12B_flatten
MT-Gen4_gemma-3-12B_flatten is a 12.19B-parameter Gemma-3 image-text-to-text merge from zelk12. Its model card documents a LazyMergekit dare_ties merge.
- Publisher
- zelk12
- Task
- image-text-to-text
- Model type
- gemma3
- License
- gemma
- Library
- Unknown
- Publication status
- Accepted · not indexed
Model overview
MT-Gen4_gemma-3-12B_flatten is published by zelk12 as an image-text-to-text model. The captured configuration identifies Gemma3ForConditionalGeneration and Safetensors metadata reports 12187325040 parameters. According to the model card, it is a LazyMergekit merge of two zelk12 Gemma-3-12B models using dare_ties.
Recorded capabilities
LazyMergekit dare_ties merge
According to the model card, two zelk12 Gemma-3-12B models were merged with LazyMergekit using dare_ties in bfloat16.
Documented density-weight config
According to the model card, the merge uses density 0.438 and 0.561 with weights 0.561 and 0.438 and normalize enabled.
Transformers pipeline example
The model card documents AutoTokenizer plus a text-generation pipeline with an explicit sampling configuration.
Use cases in the source record
- Conversational image-text-to-text experiments using the documented transformers text-generation pipeline.
- Mergekit research workflows that reuse the documented dare_ties density-weight 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 purpose and downstream behavior come from a tentative publisher description and have not been independently verified by Ethen.
Source and provenance
Source: zelk12/MT-Gen4_gemma-3-12B_flatten
Captured: Unknown. Processed: 2026-09-07T19:36:04.479465+00:00.
EN Merge to try to align the model results on the UGI leaderboard, to create the source for the modifications. In general, just a tentative description. RU Объединение, чтобы попытаться выровнять результаты модели в таблице лидеров UGI, для создания исходника для модификаций. В целом просто пробное описание. MT-Gen4_gemma-3-12B_flatten MT-Gen4_gemma-3-12B_flatten is a merge of the following models using LazyMergekit : zelk12/26_05_2025_Test_LazyMergekit_gemma-3-12B zelk12/MT4-gemma-3-12B 🧩 Configuration models: - model: zelk12/26_05_2025_Test_LazyMergekit_gemma-3-12B #no parameters necessary for base model - model: zelk12/26_05_202…
F001F002F003F004F005F006F007F008F009F010F011F014F015F016