Instructions to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Ollama
How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Ollama:
```
ollama run hf.co/SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF to start chatting

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-14B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen2.5-14B-Instruct

Qwen2.5-14B-Instruct is an instruction-aligned large language model from the Qwen family, designed for high-quality conversational interaction, structured task execution, and advanced reasoning. It is optimized to respond reliably to user prompts while maintaining coherence across long contexts and multi-turn exchanges.

The model is suitable for both research and production scenarios, supporting a wide range of natural language applications including analysis, summarization, coding assistance, and general dialogue.

Model Overview

Model Name: Qwen2.5-14B-Instruct
Base Model: Qwen2.5-14B
Architecture: Decoder-only Transformer
Parameter Count: 14 Billion
Context Window: Up to 128K tokens (implementation dependent)
Modalities: Text
Primary Languages: English, Chinese, multilingual capability
Developer: Qwen
License: Apache 2.0

Design Objectives

This model is built to deliver strong performance in real-world instruction-following environments. Key design priorities include:

Reliable adherence to user instructions
Long-context comprehension and memory retention
Robust logical and analytical reasoning
Structured and formatted output generation
Stable multi-turn conversational behavior

Quantization Details

Q4_K_M

Approx. ~71% size reduction
Very low memory footprint (~8.37 GB)
Optimized for CPU inference and low-VRAM GPUs
Faster token generation speeds
Minor degradation in complex analytical or long-chain reasoning tasks

Q5_K_M

Approx. ~66% size reduction
Better fidelity to the original FP16 model (9.79 GB)
Improved coherence and reasoning consistency
Recommended when slightly more memory is available

Training Overview

Pretraining

The base model is trained on a large and diverse multilingual corpus covering web text, code, academic material, and structured data. Training focuses on learning linguistic structure, knowledge representation, and long-range dependency modeling.

Instruction Alignment

The instruct variant is further refined using supervised fine-tuning and alignment methods to improve:

Prompt interpretation accuracy
Response clarity and usefulness
Safety and controllability
Step-by-step reasoning performance

Core Capabilities

Instruction adherence
Accurately executes complex or multi-step prompts.
Extended context processing
Handles large documents, transcripts, and long conversations.
Reasoning and problem solving
Suitable for analytical tasks, explanations, and structured thinking.
Multilingual interaction
Supports multiple languages with strong English and Chinese performance.
Structured output generation
Produces formatted responses such as lists, tables, JSON, and stepwise solutions.
Conversational consistency
Maintains topic continuity across long dialogue sessions.

Example Usage

llama.cpp

./llama-cli \
  -m SandlogicTechnologies\Qwen2.5-14B-Instruct_Q4_K_M.gguf \
  -p "Explain transformers in simple terms."

Recommended Use Cases

Conversational AI and virtual assistants
Document understanding and summarization
Research and technical explanation
Programming and code guidance
Knowledge exploration and tutoring
Long-form content generation

Acknowledgments

These quantized models are based on the original work by Qwen development team.

Special thanks to:

The Qwen team for developing and releasing the Qwen2.5-14B-Instruct model.
Georgi Gerganov and the entire llama.cpp open-source community for enabling efficient model quantization and inference via the GGUF format.

Contact

For any inquiries or support, please contact us at support@sandlogic.com or visit our Website.

Downloads last month: 7

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

Model tree for SandLogicTechnologies/Qwen2.5-14B-Instruct-GGUF

Base model

Qwen/Qwen2.5-14B

Quantized

(78)

this model