G
Gemma 4 E4B IT (GGUF Q4_0)
Google · Gemma 4
MultimodalApache-2.0publicTrusted4B params
llama.cpp GGUF build (Q4_0 QAT) of Gemma 4 E4B IT. One projector file carries BOTH encoders - clip.has_vision_encoder and clip.has_audio_encoder - so the entry reads images and speech on the GGUF consensus engine at 6.1 GB instead of the 18 GB the torch path needs.
llama.cpp GGUF build (Q4_0 QAT) of Gemma 4 E4B IT. One projector file carries BOTH encoders - clip.has_vision_encoder and clip.has_audio_encoder - so the entry reads images and speech on the GGUF consensus engine at 6.1 GB instead of the 18 GB the torch path needs.
At a glance
- Task: Multimodal (InferenceV1)
- Params: 4B
- License: Apache-2.0 (commercial use OK)
- Hardware: 7 GB+ VRAM
- dtype: Int4