kimjonguk/my-ai.Q4_K_M-v10

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 30, 2026Architecture:Transformer Featherless Exclusive Cold

The kimjonguk/my-ai.Q4_K_M-v10 model is a 3.1 billion parameter language model, fine-tuned and converted to GGUF format using Unsloth. This model is optimized for efficient deployment and inference, particularly for text-only LLM applications. Its GGUF format and included Ollama Modelfile facilitate easy integration into local inference setups. It is designed for general language tasks where a compact yet capable model is required.

Loading preview...

Overview

The kimjonguk/my-ai.Q4_K_M-v10 is a 3.1 billion parameter language model, specifically a Qwen2.5-3B-Instruct variant, provided in the efficient GGUF format. It was fine-tuned and converted using Unsloth, a framework known for accelerating training and conversion processes. This model is designed for local deployment and inference, offering a balance between performance and resource efficiency.

Key Capabilities

  • Efficient Local Inference: Provided in GGUF format, making it suitable for CPU-based inference with tools like llama-cli.
  • Instruction-Tuned: Based on the Qwen2.5-3B-Instruct architecture, indicating its capability for following instructions and engaging in conversational tasks.
  • Ollama Integration: Includes an Ollama Modelfile for streamlined deployment and management within the Ollama ecosystem.
  • Unsloth Optimization: Benefits from Unsloth's optimizations, which enable faster training and conversion, contributing to its readiness for use.

Good For

  • Developers seeking a compact, instruction-tuned model for local execution.
  • Applications requiring efficient text generation and instruction following on consumer hardware.
  • Experimentation with GGUF models and the Ollama platform.

Finetunes
1 models