qwen2.5-coder-14b-instruct-ai-workshop-poc-gguf

qwen2.5-coder-14b-instruct-ai-workshop-poc-gguf

This model is based on Qwen2.5-Coder-14B-Instruct and was fine-tuned for a focused proof-of-concept AI workshop setting. It is intended as a controlled demonstration model rather than a general-purpose coding release. While the base coding capabilities were preserved, the model was optimized for a narrow workshop scenario and should be evaluated in that context before broader use.

Repository contents

This repository contains GGUF exports for local runtimes such as LM Studio and llama.cpp.

The GGUF files are intentionally stored at the repository root so quantization variants are easier for LM Studio and other GGUF tools to discover.

Available quantizations

• qwen2.5-coder-14b-instruct-ai-workshop-poc.Q8_0.gguf
• qwen2.5-coder-14b-instruct-ai-workshop-poc.Q6_K.gguf
• qwen2.5-coder-14b-instruct-ai-workshop-poc.Q5_K_M.gguf

Recommendation

Use Q8_0 first if you want the closest result to the validated release.

Use Q6_K if you want a smaller file with very strong quality.

Use Q5_K_M if you want the lightest option in this release.