ComfyUI Gemma 3 4b It
Single file version of gemma-3-4b-it, used by NewBie-Image. It can be directly loaded in ComfyUI using the Load CLIP node with type lumina2.
Model source
- Kind
- Text model
- File size
- 7.23 GB
- Version
- vBF16
- Updated
- Oct 28, 2026
- Downloads
- 0
- Source
- Hugging Face
Source description
Single file version of gemma-3-4b-it, used by NewBie-Image. It can be directly loaded in ComfyUI using the Load CLIP node with type lumina2.
Its format is similar to https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/text_encoders/gemma_2_2b_fp16.safetensors . Only language_model in the original gemma3-4b-it included here, while multi_modal_projector and vision_tower are not. The official NewBie-Image actually has the ability to encode images as prompts, and I'm leaving it for future work.
The tokenizer is included as the tensor spiece_model.
Sources
1 source
Sources
1 sourceVerified Oct 28
Model artifacts
1 artifact
Model artifacts
1 artifactgemma_3_4b_it_bf16.safetensors
safetensors · BF16 (unverified) · 7.23 GB · SHA-256 9ca0ed0c8b00…8d6e · Hugging Face
Download fileSource excerpts
2 excerpts
Source excerpts
2 excerptsSingle file version of gemma-3-4b-it, used by NewBie-Image. It can be directly loaded in ComfyUI using the Load CLIP node with type `lumina2`. Its format is similar to https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/text_encoders/gemma_2_2b_fp16.safetensors . Only `language_model` in the original gemma3-4b-it included here, while `multi_modal_projector` and `vision_tower` are not. The official NewBie-Image actually has the ability to encode images as prompts, and I'm leaving it for future work. The tokenizer is included as the tensor `spiece_model`.
Source context: 0 downloads · 0 likes · Repo woctordho/comfyui-gemma-3-4b-it
