Model Catalog
Gemma
Google's lightweight open models prove great things come in small packages. Built from the same technology that powers Gemini, they deliver strong reasoning, coding, and conversational skills. Capable enough for serious work, yet compact enough to run almost anywhere.
9 items
google
gemma-4-12B-it
Any-to-Any
vLLM Engine
Apache 2.0 License
GPU 1x Nvidia L40S
$ 1.8
ggml-org
gemma-4-26B-A4B-it-GGUF
/
Q4_K_M
LlamaCpp Quantization
Image-Text-to-Text
Llama.cpp Engine
Apache 2.0 License
GPU 1x Nvidia L4
$ 0.8
google
gemma-4-31B-it
Deployed 179 times
Image-Text-to-Text
vLLM Engine
Apache 2.0 License
GPU 2x Nvidia H200
$ 10
google
gemma-4-26B-A4B-it
Image-Text-to-Text
vLLM Engine
Apache 2.0 License
GPU 1x Nvidia H200
$ 5
google
embeddinggemma-300m
Sentence Similarity
TEI Engine
Gemma License
CPU 2x Intel Sapphire Rapids
$ 0.067
onnx-community
embeddinggemma-300m-ONNX
Sentence Similarity
TEI Engine
Gemma License
CPU 2x Intel Sapphire Rapids
$ 0.067
BAAI
bge-multilingual-gemma2
Feature Extraction
Default Engine
Gemma License
GPU 1x Nvidia L40S
$ 1.8
google
gemma-3-12b-it
Deployed 264 times
Image-Text-to-Text
vLLM Engine
Gemma License
GPU 1x Nvidia L40S
$ 1.8
google
gemma-3-27b-it
Deployed 312 times
Image-Text-to-Text
vLLM Engine
Gemma License
GPU 1x Nvidia A100
$ 2.5