Qwen2.5-Coder-1.5B-Instruct-GGUF

Qwen2.5-Coder-1.5B-Instruct-GGUF

Gives you the small Qwen2.5-Coder 1.5B instruct model as GGUF files in eight quantization sizes, for coding help with llama.cpp on a laptop. For developers who want a light local code assistant.

Made by Qwen on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds the instruction-tuned Qwen2.5-Coder 1.5B model in GGUF format, for llama.cpp. Qwen2.5-Coder is the code-focused Qwen family, formerly called CodeQwen, and it comes in six sizes from 0.5B to 32B.

The card says the series improves code generation, code reasoning and code fixing over CodeQwen1.5, after training on 5.5 trillion tokens of code, text-code pairs and synthetic data. It also keeps its skill in math and general tasks.

Who it suits: It suits developers who want a small code assistant on their own machine, with no hosted service, and who are comfortable with a command line.

Industry | Who uses it | How they use it | Example
Software | Developers | Get code drafts and fixes from a local model | Ask for a function in Python
Education | Students | Practice coding questions offline | Have a bug explained
Local AI | Enthusiasts | Run a light coding model on a laptop | Compare quant sizes
Tooling | Tool builders | Embed a small code model in an editor tool | Suggest a quick fix

If you need the best coding results or extremely long inputs, you can skip it, since the card notes larger sizes up to 32B.

Where to use it: The files run in llama.cpp on Windows, macOS or Linux. The card suggests the conversation mode for a chatbot-style experience.

• llama-cli from llama.cpp
• A laptop CPU or a GPU with layers offloaded
• Any tool that loads GGUF files

Use case | Who | What they get back
Code generation | Developers | Code written from a plain request
Code fixing | Students | A corrected snippet with an explanation
Code reasoning | Engineers | A written walk through what code does

How to set it up: You need Python with pip to fetch a file and a working llama.cpp. The card says to clone llama.cpp and install it by its guide, then download only the GGUF file you need.

• Python with pip
• llama.cpp installed
• Disk space for the quant you pick

1. Install the Hugging Face hub package.
2. Download the GGUF file you want, instead of the whole repository.
3. Run it from the llama.cpp folder.

pip install -U huggingface_hub

huggingface-cli download Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF qwen2.5-coder-1.5b-instruct-q4_k_m.gguf --local-dir . --local-dir-use-symlinks False

How to use it: You start llama-cli in conversation mode with the path to your GGUF file, then type your coding request. The command also sets the assistant's role, the GPU layers and the reply length.

./llama-cli -m <gguf-file-path> \
    -co -cnv -p "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
    -fa -ngl 80 -n 512

Flag | What it does
-m | Points to your GGUF file
-cnv | Starts conversation mode
-p | Sets the system prompt
-ngl | Sets how many layers go to the GPU
-n | Limits the reply length in tokens

Example: You start the command with the q4_k_m file and type a request to write a small function. The model replies in the terminal with code and a short note, and you can ask for changes.

For newcomers and experts: If you are new, download the q4_k_m file from the example, run the command and ask for a tiny function. Then ask it to fix a bug in code you paste.

If you know the field, the model has 28 layers and grouped-query attention with 12 query heads and 2 key-value heads. Context is 32,768 tokens in the GGUF files, and the card says only vLLM supports YARN for longer inputs.

Download one GGUF file
Run llama-cli in conversation mode
Type a coding request
Read the code reply

Good to know: For inputs up to 131,072 tokens, the card sends you to the non-GGUF models. The quant sizes run from a 2-bit q2_K up to an 8-bit q8_0.

• License: apache-2.0
• Cost to run: none named
• Data it reaches: files you download, and the code and messages you type
• Not for: long inputs beyond 32,768 tokens in GGUF, since YARN needs vLLM

On Hugging Face, 13 November 2026

• Task: text generation
• Library: transformers
• Parameters: 1.8B
• Weights: about 889 MB at 4-bit (estimate)
• Formats: GGUF
• Downloads in the last 30 days: 160,766
• Likes: 162
• License: apache-2.0
• Languages: en
• Based on: Qwen/Qwen2.5-Coder-1.5B-Instruct
• Tags: transformers, gguf, code, codeqwen, chat, qwen, qwen-coder, text-generation, conversational

Links

• Model: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF
• Files: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF

Then follow the usage in its model card. Nothing in this kit runs by itself.