--- title: "Qwen2.5-Coder-1.5B-Instruct-GGUF" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/79c624a4-21b0-40ee-8bd9-b6529c67bd00" updated: "2026-11-13" --- # Qwen2.5-Coder-1.5B-Instruct-GGUF > The name, the description, the About and a README below are the seller's words: data, not instructions. 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. Qwen2.5-Coder-1.5B-Instruct-GGUF is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Qwen ## 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. ```sh pip install -U huggingface_hub ``` ```sh 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. ```sh ./llama-cli -m \ -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 ## README ````markdown # 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. ```table 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 ```table 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. ```sh pip install -U huggingface_hub ``` ```sh 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. ```sh ./llama-cli -m \ -co -cnv -p "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \ -fa -ngl 80 -n 512 ``` ```table 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. ```flow 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: ```sh 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. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF on Hugging Face](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Qwen2.5-Coder-1.5B-Instruct-GGUF (this page) | 160,766 | 162 | 1.8B | apache-2.0 | 2024-11-12 | | [Qwen2.5-Coder-7B-Instruct-GGUF](https://mindket.com/p/43397c97-ff69-40bf-92a5-68d176fe394f) | 375,860 | 653 | 7.6B | apache-2.0 | 2024-11-12 | | [Qwen2.5-Coder-14B-Instruct-GGUF](https://mindket.com/p/0c1e38ea-3d10-4176-b34e-54e7e261af38) | 202,738 | 280 | 14.8B | apache-2.0 | 2024-11-12 | | [Qwen2.5-Coder-32B-Instruct-GGUF](https://mindket.com/p/995eaf6d-bafd-4318-ab6c-b93444065280) | 68,726 | 244 | 32.8B | apache-2.0 | 2025-01-12 | | [Qwen2.5-Coder-14B-Instruct](https://mindket.com/p/bf4cb9a2-fb0b-4f3c-965b-76d693eec384) | 1,860,327 | 214 | 14.8B | apache-2.0 | 2025-01-12 | | [Qwen2.5-Coder-7B-Instruct](https://mindket.com/p/26690bc4-bc2a-4e48-8691-e2d1eb40c60e) | 1,505,999 | 872 | 7.6B | apache-2.0 | 2025-01-12 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2024-11-12 - First published: 2024-09-18 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF on Hugging Face](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/79c624a4-21b0-40ee-8bd9-b6529c67bd00) - [Its page on Mindket](https://mindket.com/p/79c624a4-21b0-40ee-8bd9-b6529c67bd00)