75 Pulls 1 Tag Updated 7 months ago
Google gemma3 with added tools support.
17.4K Pulls 3 Tags Updated 8 months 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.
11K Pulls 5 Tags Updated 6 months ago
Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)
6,567 Pulls 8 Tags Updated 7 months ago
The current, most capable model that runs on a single GPU or TPU. Now with tools
6,512 Pulls 2 Tags Updated 8 months ago
The current, most capable model that runs on a single GPU. With quantization and tools.
1,683 Pulls 3 Tags Updated 8 months ago
Gemma3, but with vision AND tool calling?! What could be better than that?
953 Pulls 3 Tags Updated 8 months ago
A Gemma3 model with integrated tool support, fully compatible with the latest Ollama release.
944 Pulls 4 Tags Updated 5 months ago
912 Pulls 3 Tags Updated 9 months ago
812 Pulls 4 Tags Updated 9 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.
556 Pulls 2 Tags Updated 8 months ago
Gemma3n with tools
447 Pulls 2 Tags Updated 5 months ago
The current, most capable model that runs on a single GPU with Tools Support
416 Pulls 3 Tags Updated 9 months ago
Enhanced function (tool) calling capabilities with modified template as supposed by Philipp Schmid (Google DeepMind) for gemma3 models.
264 Pulls 1 Tag Updated 8 months ago
229 Pulls 4 Tags Updated 4 months ago
Gemma 3 with tools
88 Pulls 1 Tag Updated 1 month ago
68 Pulls 1 Tag Updated 4 months ago
gemma3:12b-it-qat with tool support
65 Pulls 1 Tag Updated 2 months ago
58 Pulls 1 Tag Updated 8 months ago
49 Pulls 1 Tag Updated 9 months ago