gemma3

The current, most capable model that runs on a single GPU.

vision cloud 270m 1b 4b 12b 27b

28.4M Pulls 29 Tags Updated 1 week ago

gemma3n

Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.

e2b e4b

911K Pulls 9 Tags Updated 5 months ago

functiongemma

FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

270m

201 Pulls 4 Tags Updated 16 hours ago

embeddinggemma

EmbeddingGemma is a 300M parameter embedding model from Google.

embedding 300m

327.4K Pulls 5 Tags Updated 3 months ago

glm4

A strong multi-lingual general language model with competitive performance to Llama 3.

9b

190.8K Pulls 32 Tags Updated 1 year ago

zongwei/gemma3-translator

This model, based on the gemma3 model, is specifically designed to perform high quality translations between multiple languages.

vision 1b 4b

101.7K Pulls 2 Tags Updated 8 months ago

huihui_ai/gemma3-abliterated

The current, most capable model that runs on a single GPU.

vision 270m 1b 4b 12b 27b

49.2K Pulls 16 Tags Updated 3 months ago

PetrosStav/gemma3-tools

Google gemma3 with added tools support.

vision tools 4b 12b 27b

17.4K Pulls 3 Tags Updated 8 months ago

scb10x/typhoon2.1-gemma3-4b

Typhoon2.1 4B - 4B parameters Thai / English bilingual LLM build based on Gemma3.

tools

16.8K Pulls 1 Tag Updated 7 months ago

huihui_ai/gemma3n-abliterated

This is an uncensored version of google/gemma-3n created with abliteration

14.9K Pulls 2 Tags Updated 5 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

11K Pulls 5 Tags Updated 6 months ago

pidrilkin/gemma3_27b_abliterated

vision

7,029 Pulls 1 Tag Updated 8 months ago

mdq100/Gemma3-Instruct-Abliterated

Gemma3-Instruct-Abliterated model is an instruction-tuned, abliterated, and uncensored AI model built on the Gemma-3 instruction-tuned model from Hugging Face. This Ollama model provides free, honest, and uncensored responses while remaining coherent

vision 12b 27b

6,965 Pulls 2 Tags Updated 2 months ago

orieg/gemma3-tools

Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)

vision tools 1b 4b 12b 27b

6,567 Pulls 8 Tags Updated 7 months ago

Hituzip/gemma3-tools

The current, most capable model that runs on a single GPU or TPU. Now with tools

vision tools 4b

6,512 Pulls 2 Tags Updated 8 months ago

ebdm/gemma3-enhanced

Gemma 3 enhanced with Tool Calling support [128k context window + multimodal]

vision tools 12b

2,599 Pulls 1 Tag Updated 9 months ago

mychen76/gemma3_cline_roocode_qat

Quantized version of Gemma3-12B,27B optimized for tool usage in Cline / Roo Code and complex problem solving.

vision tools 12b 27b

1,929 Pulls 2 Tags Updated 7 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.

1,880 Pulls 1 Tag Updated 8 months ago

kwangsuklee/gemma-3-12b-it-Q4_K_M

25.3.12. Gemma3-12B-it(instruction) Q4_K_M (7.3GB)

1,711 Pulls 1 Tag Updated 9 months ago

mix_77/gemma3-qat-tools

The current, most capable model that runs on a single GPU. With quantization and tools.

vision tools 4b 12b 27b

1,683 Pulls 3 Tags Updated 8 months ago