Gemma Family: Google Open Text Encoder Models for ComfyUI

Gemma is Google DeepMind's family of open models for use as ComfyUI text encoders, including Gemma 4 with E2B and E4B instruction-tuned variants.

G

Gemma by Google DeepMind

Text EncoderMultimodalOpen SourceApache 2.0

Family of open models built by Google DeepMind. Gemma 4 models are multimodal (text and image) with configurable thinking modes, supporting a context window of up to 256K tokens and over 140 languages. Available in E2B (2.3B effective) and E4B (4.5B effective) instruction-tuned variants, packaged as ComfyUI text encoders.

Models

ModelDescriptionLicenseReleased
Gemma 4Instruction-tuned text encoders for ComfyUI with E2B and E4B variants in BF16 and FP8Apache 2.02025-07

Select a model above for curated weight downloads, tutorials, and related information.