The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.
130.6K Pulls 33 Tags Updated 11 months ago
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
103.5K Pulls 33 Tags Updated 1 year ago
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
126.7K Pulls 17 Tags Updated 1 week ago
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
3.4M Pulls 9 Tags Updated 10 months ago
This is a modified model that adds support for autonomous coding agents like Cline
555.4K Pulls 6 Tags Updated 8 months ago
Qwen2.5 coder tools model can work with Cline (prev. Claude Dev). Update 0.5b, 1.5b, 3b, 7b, 14b, 32b coder models.
41.1K Pulls 15 Tags Updated 12 months ago
This version of Deepseek R1 is optimized for tool usage with Cline and Roo Code.
16.6K Pulls 510 Tags Updated 8 months ago
Google gemma3 with added tools support.
15.9K Pulls 3 Tags Updated 6 months ago
Qwen2.5 coder tools model can work with Cline (prev. Claude Dev).
11.3K Pulls 13 Tags Updated 11 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.
10.4K Pulls 5 Tags Updated 5 months ago
The current, most capable model that runs on a single GPU or TPU. Now with tools
6,416 Pulls 2 Tags Updated 7 months ago
Gemma3 model with tools support and large context window (optimized for RTX3090 24GB VRAM)
5,408 Pulls 8 Tags Updated 6 months ago
Many quantized GGUF versions of deepseek R1 abliterated (uncensored) with tools support
4,363 Pulls 8 Tags Updated 9 months ago
Phi4 with tool support
2,586 Pulls 1 Tag Updated 9 months ago
Qwen2 with tools enabled
2,109 Pulls 3 Tags Updated 1 year ago
1,769 Pulls 6 Tags Updated 8 months ago
The current, most capable model that runs on a single GPU. With quantization and tools.
1,622 Pulls 3 Tags Updated 6 months ago
Deepseek R1 optimized for tool usage with Cline.
1,591 Pulls 3 Tags Updated 8 months ago
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft. Clone of `phi4` with a tool calling template.
1,439 Pulls 1 Tag Updated 9 months ago
DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1. Compatible with Cline. Distill Versions are available! <3
1,258 Pulls 20 Tags Updated 9 months ago