Instructions to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_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 MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
# Run inference directly in the terminal:
llama cli -hf MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
# Run inference directly in the terminal:
llama cli -hf MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

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 MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
# Run inference directly in the terminal:
./llama-cli -hf MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

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 MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

Use Docker

docker model run hf.co/MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

LM Studio
Jan
Ollama
How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF with Ollama:
```
ollama run hf.co/MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
```

Unsloth Studio

How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_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 MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_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 MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF to start chatting

Docker Model Runner
How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF with Docker Model Runner:
```
docker model run hf.co/MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF
```

Lemonade

How to use MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF

Run and chat with the model

lemonade run user.Hercules-Qwen1.5-14B_iMatrix_GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

GGUFs for Hercules-Qwen 1.5 14B - https://huggingface.co/M4-ai/Hercules-Qwen1.5-14B

iMatrix GGUFs generated with Kalomaze's semi-random groups_merged.txt

Downloads last month: 102

GGUF

Model size

14B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

MarsupialAI
/

Hercules-Qwen1.5-14B_iMatrix_GGUF

Dataset used to train MarsupialAI/Hercules-Qwen1.5-14B_iMatrix_GGUF