tensorblock/RoadQAQ_Qwen2.5-Math-1.5B-16k-think-GGUF

RoadQAQ/Qwen2.5-Math-1.5B-16k-think - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for RoadQAQ/Qwen2.5-Math-1.5B-16k-think.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

Your task is to follow a systematic, thorough reasoning process before providing the final solution. This involves analyzing, summarizing, exploring, reassessing, and refining your thought process through multiple iterations. Structure your response into two sections: Thought and Solution. In the Thought section, present your reasoning using the format: “<think>
 {thoughts} </think>
”. Each thought should include detailed analysis, brainstorming, verification, and refinement of ideas. After “</think>
,” in the Solution section, provide the final, logical, and accurate answer, clearly derived from the exploration in the Thought section. If applicable, include the answer in oxed{} for closed-form results like multiple choices or mathematical solutions. User: This is the problem:
{prompt}
Assistant: <think>

Model file specification

Filename	Quant type	File Size	Description
Qwen2.5-Math-1.5B-16k-think-Q2_K.gguf	Q2_K	0.676 GB	smallest, significant quality loss - not recommended for most purposes
Qwen2.5-Math-1.5B-16k-think-Q3_K_S.gguf	Q3_K_S	0.761 GB	very small, high quality loss
Qwen2.5-Math-1.5B-16k-think-Q3_K_M.gguf	Q3_K_M	0.824 GB	very small, high quality loss
Qwen2.5-Math-1.5B-16k-think-Q3_K_L.gguf	Q3_K_L	0.880 GB	small, substantial quality loss
Qwen2.5-Math-1.5B-16k-think-Q4_0.gguf	Q4_0	0.935 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2.5-Math-1.5B-16k-think-Q4_K_S.gguf	Q4_K_S	0.940 GB	small, greater quality loss
Qwen2.5-Math-1.5B-16k-think-Q4_K_M.gguf	Q4_K_M	0.986 GB	medium, balanced quality - recommended
Qwen2.5-Math-1.5B-16k-think-Q5_0.gguf	Q5_0	1.099 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2.5-Math-1.5B-16k-think-Q5_K_S.gguf	Q5_K_S	1.099 GB	large, low quality loss - recommended
Qwen2.5-Math-1.5B-16k-think-Q5_K_M.gguf	Q5_K_M	1.125 GB	large, very low quality loss - recommended
Qwen2.5-Math-1.5B-16k-think-Q6_K.gguf	Q6_K	1.273 GB	very large, extremely low quality loss
Qwen2.5-Math-1.5B-16k-think-Q8_0.gguf	Q8_0	1.647 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/RoadQAQ_Qwen2.5-Math-1.5B-16k-think-GGUF --include "Qwen2.5-Math-1.5B-16k-think-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/RoadQAQ_Qwen2.5-Math-1.5B-16k-think-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'