Gargantua 2.5: the main openTARS assistant on Gemma 4 E4B. Uses your computer’s tools, sees the screen and understands audio. Runs locally.
Gargantua Pro Gen 1: our largest model, Gemma 4 12B fine-tuned for openTARS tools, with vision. For computers with room for 8 GB or more.
v2 is built for coding + agentic work — writing code, running commands, using tools, debugging, multi-step technical tasks.
Agentic coding model for 24 GB GPUs: TeichAI's Gemma-4-31B Fable-5 agent distill (vision + thinking + tools) with a disciplined coding-agent system prompt baked in. Inspect → reproduce → smallest fix → re-verify.
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of https://ollama.com/library/gemma3:1b.
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. It requires bigger value for num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of https://ollama.com/library/gemma4:26b.
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. It requires bigger value for num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of official qat of gemma4-26b
Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)
Google gemma3 with added tools support.
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.
Gemma 3 with tools
A Gemma3 model with integrated tool support, fully compatible with the latest Ollama release.
The current, most capable model that runs on a single GPU or TPU. Now with tools
Gemma 2 with tool call support
The current, most capable model that runs on a single GPU. With quantization and tools.
Gemma3n with tools
Gemma3, but with vision AND tool calling?! What could be better than that?
gemma3:12b-it-qat with tool support