85 Pulls 1 Tag Updated 11 months ago
Gemma 3 with tools
1,083 Pulls 1 Tag Updated 4 months ago
Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)
16.5K Pulls 5 Tags Updated 3 days ago
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.
12.6K Pulls 5 Tags Updated 10 months ago
A Gemma3 model with integrated tool support, fully compatible with the latest Ollama release.
2,973 Pulls 4 Tags Updated 9 months ago
Quantized version of Gemma3-12B,27B optimized for tool usage in Cline / Roo Code and complex problem solving.
2,365 Pulls 2 Tags Updated 11 months ago
35 Pulls 2 Tags Updated 5 months ago
The current, most capable model that runs on a single GPU. With quantization and tools.
1,801 Pulls 3 Tags Updated 11 months ago
gemma3:12b-it-qat with tool support
529 Pulls 1 Tag Updated 6 months ago
Gemma3n with tools
636 Pulls 2 Tags Updated 8 months ago
Gemma3:12b, with added tools, quantized to Q2_K and Q3_K_S for GPU with 8gb Vram or less. Vision module fully working.
695 Pulls 2 Tags Updated 12 months ago
429 Pulls 4 Tags Updated 8 months ago
485 Pulls 1 Tag Updated 10 months ago
Gemma 3 with tool calling support
391 Pulls 2 Tags Updated 7 months ago
Google Gemma 3n | Edge AI with tool support. Designed for consumer devices: efficient, local, tool-enabled
324 Pulls 1 Tag Updated 8 months ago
Enhanced function (tool) calling capabilities with modified template as supposed by Philipp Schmid (Google DeepMind) for gemma3 models.
386 Pulls 1 Tag Updated 11 months ago
Google Gemma 3n | Edge AI with tool support Designed for consumer devices: efficient, local, tool-enabled
137 Pulls 1 Tag Updated 8 months ago
104 Pulls 1 Tag Updated 7 months ago
Gemma3n E4B fine-tuned for function calling
51 Pulls 1 Tag Updated 7 months ago
54 Pulls 4 Tags Updated 9 months ago