Gemma 4 E4B It Q4 K M v2
This submission is fully structured to run seamlessly on both vLLM and llama.cpp evaluation endpoints.
Modellquelle
- Art
- Text model
- Dateigröße
- 4,97 GB
- Version
- vQ4_K
- Aktualisiert
- 30. Okt. 2026
- Downloads
- 92
- Quelle
- Hugging Face
Quellenbeschreibung
This submission is fully structured to run seamlessly on both vLLM and llama.cpp evaluation endpoints.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 30. Okt.
Download files
Repository files
File inventory only; completeness is unverified.
Modellartefakte
1 Artefakt
Modellartefakte
1 Artefaktgemma-4-q4_k_m.gguf
gguf · Q4_K (unverified) · 4,97 GB · SHA-256 e626af668f08…5fc0 · Hugging Face
Download fileQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: gemma tags: - multimodal - image-to-text - vision - gguf - quantization - energy-efficiency model_creator: Google model_name: Gemma-4-E4B-it-Q4_K_M-v2 pipeline_tag: image-to-text --- This submission is fully structured to run seamlessly on both vLLM and llama.cpp evaluation endpoints.
Source context: 92 downloads · 1 likes · Pipeline image-to-text · Repo axelbrons/gemma-4-E4B-it-Q4_K_M-v2
Source context: 132 downloads · 1 likes · Pipeline image-to-text · Repo axelbrons/gemma-4-E4B-it-Q4_K_M-v2
