Instructions to use worstplayer/gemma-3-27b-it-heretic-v2-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 worstplayer/gemma-3-27b-it-heretic-v2-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 worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_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 worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_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 worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M

Use Docker

docker model run hf.co/worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M

LM Studio
Jan

vLLM

How to use worstplayer/gemma-3-27b-it-heretic-v2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "worstplayer/gemma-3-27b-it-heretic-v2-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": "worstplayer/gemma-3-27b-it-heretic-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M

Ollama
How to use worstplayer/gemma-3-27b-it-heretic-v2-GGUF with Ollama:
```
ollama run hf.co/worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
```
Unsloth Desktop
Docker Model Runner
How to use worstplayer/gemma-3-27b-it-heretic-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M
```

Lemonade

How to use worstplayer/gemma-3-27b-it-heretic-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull worstplayer/gemma-3-27b-it-heretic-v2-GGUF:IQ3_M

Run and chat with the model

lemonade run user.gemma-3-27b-it-heretic-v2-GGUF-IQ3_M

List all available models

lemonade list

Atomic Chat

GGUF quantized versions of https://huggingface.co/coder3101/gemma-3-27b-it-heretic-v2

Multimodal projector included.

Provided quants:

IQ3_XS - 12-16GB GPUs
IQ3_M - 16GB GPUs - slightly better quality but requires offloading the KV cache at long contexts
IQ4_XS - 24GB GPUs

Downloads last month: 30

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

3-bit

4-bit

Model tree for worstplayer/gemma-3-27b-it-heretic-v2-GGUF

Base model

google/gemma-3-27b-pt

Finetuned

coder3101/gemma-3-27b-it-heretic-v2

Quantized

(4)

this model