98 Pulls 1 Tag Updated 1 year ago
Gemma 3 with tools
1,242 Pulls 1 Tag Updated 8 months ago
Gemma3n with tools
787 Pulls 2 Tags Updated 12 months ago
gemma3:12b-it-qat with tool support
657 Pulls 1 Tag Updated 9 months ago
550 Pulls 4 Tags Updated 11 months ago
138 Pulls 1 Tag Updated 11 months ago
Gemma3n E4B fine-tuned for function calling
60 Pulls 1 Tag Updated 11 months ago
Google gemma3 with added tools support.
21.4K Pulls 3 Tags Updated 1 year ago
Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)
19.4K Pulls 5 Tags Updated 3 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.
13.3K Pulls 5 Tags Updated 1 year ago
37 Pulls 2 Tags Updated 9 months ago
The current, most capable model that runs on a single GPU or TPU. Now with tools
6,685 Pulls 2 Tags Updated 1 year ago
28 Pulls 2 Tags Updated 11 months ago
A Gemma3 model with integrated tool support, fully compatible with the latest Ollama release.
4,483 Pulls 4 Tags Updated 1 year ago
The current, most capable model that runs on a single GPU. With quantization and tools.
1,839 Pulls 3 Tags Updated 1 year ago
Raw gemma3 with tool support
17 Pulls 1 Tag Updated 11 months ago
Gemma3, but with vision AND tool calling?! What could be better than that?
1,111 Pulls 3 Tags Updated 1 year ago
1,008 Pulls 3 Tags Updated 1 year ago
859 Pulls 4 Tags Updated 1 year 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.
767 Pulls 2 Tags Updated 1 year ago