Google · Ollama Search

embeddinggemma

EmbeddingGemma is a 300M parameter embedding model from Google.

embedding 300m

101.6K Pulls 5 Tags Updated 1 month ago

gemma2

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.

2b 9b 27b

8.4M Pulls 94 Tags Updated 1 year ago

gemma

Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1

2b 7b

5.4M Pulls 102 Tags Updated 1 year ago

PetrosStav/gemma3-tools

Google gemma3 with added tools support.

vision tools 4b 12b 27b

15.4K Pulls 3 Tags Updated 6 months ago

aliafshar/gemma3-it-qat-tools

Gemma3 instruction-tuned and quantized with tool/functions using a faithful representation of the Google DeepMind recommended tool calling methodology. Runs remarkably well on old GPUs and CPU.

vision tools 1b 4b 12b 27b

10.1K Pulls 5 Tags Updated 4 months ago

jaahas/gemma-2-9b-it-abliterated

Abliterated version of Google's Gemma 2 9B

6,379 Pulls 1 Tag Updated 1 year ago

jaahas/tiger-gemma-v2

Uncensored version of Google's Gemma 2 9B

2,806 Pulls 1 Tag Updated 1 year ago

todorov/bggpt

BgGPT is a Bulgarian language model built on top of Google’s Gemma 2.

1,528 Pulls 24 Tags Updated 10 months ago

mshojaei77/gemma3persian

A 4B-parameter Persian-specialized language model built on Google's Gemma 3 architecture, fine-tuned on high-quality Persian text data while preserving multimodal capabilities for native-quality responses.

1,488 Pulls 1 Tag Updated 6 months ago

tripolskypetr/gemma3-tools

Google gemma3 with added tools support.

vision tools 4b 12b 27b

900 Pulls 3 Tags Updated 7 months ago

mannix/gemma2-9b

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models

620 Pulls 24 Tags Updated 1 year ago

jslin/gemma2-it-tw

本模型是以林彥廷 TaiwanChat 資料集微調 Google 的 Gemma2:2b - it，使該模型具備較多的繁體中文語彙來進行對話。

2b

374 Pulls 1 Tag Updated 11 months ago

mannix/gemma2-2b

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models

233 Pulls 11 Tags Updated 1 year ago

antony66/gemma3-tools

Enhanced function (tool) calling capabilities with modified template as supposed by Philipp Schmid (Google DeepMind) for gemma3 models.

vision tools 27b

228 Pulls 1 Tag Updated 6 months ago

jwang580/medgemma_27b_text_it

MedGemma is a Gemma 3 variants that are trained for performance on medical text and image comprehension developed by Google. 27B is text only. For all MedGemma 27B results, test-time scaling is used to improve performance. This is the full version.

190 Pulls 1 Tag Updated 4 months ago