Marketplace

Fine-tuned Llama 3.1 8B model specialized for function calling tasks, trained on the xlam-function-calling-60k dataset using reward-model-filtered data.

Quantized GGUF version of DeepSeek Coder 6.7B fine-tuned for chat and function calling with OpenAI-compatible syntax. Multiple quantization levels available from 2.36GB to 6.67GB.

Use IBM's Granite-20B-FunctionCalling model to enable multi-task function calling capabilities including nested functions, function chaining, parallel execution, and intelligent parameter detection for AI agents.

A finetuned CodeLlama-7b model specialized in code completion, generation, refactoring, and documentation across Python, C++, Java, and JavaScript.

A compact 1.2B parameter liquid neural network model specialized in function calling and tool use, optimized for conversational AI applications with structured function execution capabilities.

A dynamic multi-expert LLM system that routes questions to specialized models (programming, biology, mathematics) using keyword matching and a director model for optimal domain-specific responses.

Development assistant for gatsby-theme-chronogrove, a Gatsby theme monorepo powering a personal website with social dashboard widgets. Helps with decoupling personal content, widget development, testing, and theme configuration.

A specialized AI agent model focused on security, safety, and agent-based tasks. Based on Llama 3.1 8B architecture, fine-tuned for security analysis and conversational safety assessment. Available in multiple GGUF quantization formats optimized for different hardware constraints.

Expert AI assistant for React, TypeScript, and Nx monorepo development for HAQQ blockchain applications. Specializes in wagmi, viem, blockchain integration, and monorepo best practices.

Expert Next.js development guidelines for building optimized, maintainable developer tools with TypeScript, React, and modern UI frameworks. Focuses on standardized tool structure, performance optimization, and comprehensive documentation.

Assess sentiment of text across 100+ languages using a fine-tuned E5-small model. Returns numeric sentiment scores for filtering, analysis, and content moderation in multilingual contexts.

Turkish-English bilingual Llama 3 8B model fine-tuned for function calling and tool use, optimized for Turkish language understanding with GGUF quantization support

Fine-tuned 270M parameter Gemma model specialized for simple function/tool calling tasks with conversational capabilities

Generate structured function calls and tool invocations using Groq's Llama 3 70B model fine-tuned for tool use and function calling. Excels at API interactions, structured data manipulation, and complex multi-step tool orchestration.

Llama-3 based model fine-tuned by Groq for advanced function calling and tool use, available in GGUF format for local inference with various quantization options

A 2.6B parameter Bulgarian language model optimized for function calling, tool use, and MCP integration. Available in multiple GGUF quantization formats for efficient local inference.

Evaluate function calls in Model Context Protocol (MCP) tools. Assess correctness, tool selection, parameter names, and parameter values using a fine-tuned Qwen2.5-0.5B model.

GGUF quantized version of Llama 3 70B optimized for tool use and function calling. Includes multiple quantization levels from IQ1_S (15.4GB) to Q6_K (58GB) to balance quality and performance based on available hardware.

Bulgarian language model specialized in function calling, tool use, and MCP (Model Context Protocol) integration. Based on Tucan-9B-v1.0 with enhanced tool-use capabilities.

Quantized GGUF model files for Llama-3-Groq-8B-Tool-Use, optimized for function calling and tool use with llama.cpp compatibility