Instructions to use fedric95/gemma-2-2b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fedric95/gemma-2-2b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="fedric95/gemma-2-2b-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fedric95/gemma-2-2b-GGUF", dtype="auto")

llama-cpp-python

How to use fedric95/gemma-2-2b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fedric95/gemma-2-2b-GGUF",
	filename="gemma-2-2b-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use fedric95/gemma-2-2b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fedric95/gemma-2-2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf fedric95/gemma-2-2b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fedric95/gemma-2-2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf fedric95/gemma-2-2b-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 fedric95/gemma-2-2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf fedric95/gemma-2-2b-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 fedric95/gemma-2-2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fedric95/gemma-2-2b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/fedric95/gemma-2-2b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use fedric95/gemma-2-2b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fedric95/gemma-2-2b-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": "fedric95/gemma-2-2b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fedric95/gemma-2-2b-GGUF:Q4_K_M

SGLang

How to use fedric95/gemma-2-2b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "fedric95/gemma-2-2b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fedric95/gemma-2-2b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "fedric95/gemma-2-2b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fedric95/gemma-2-2b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use fedric95/gemma-2-2b-GGUF with Ollama:
```
ollama run hf.co/fedric95/gemma-2-2b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use fedric95/gemma-2-2b-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 fedric95/gemma-2-2b-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 fedric95/gemma-2-2b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fedric95/gemma-2-2b-GGUF to start chatting

Docker Model Runner
How to use fedric95/gemma-2-2b-GGUF with Docker Model Runner:
```
docker model run hf.co/fedric95/gemma-2-2b-GGUF:Q4_K_M
```

Lemonade

How to use fedric95/gemma-2-2b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fedric95/gemma-2-2b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2-2b-GGUF-Q4_K_M

List all available models

lemonade list

Llamacpp Quantizations of Meta-Llama-3.1-8B

Using llama.cpp release b3583 for quantization.

Original model: https://huggingface.co/google/gemma-2-2b

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Perplexity (wikitext-2-raw-v1.test)
gemma-2-2b.FP32.gguf	FP32	10.50GB	8.9236 +/- 0.06373
gemma-2-2b-Q8_0.gguf	Q8_0	2.78GB	8.9299 +/- 0.06377
gemma-2-2b-Q6_K.gguf	Q6_K	2.15GB	8.9570 +/- 0.06404
gemma-2-2b-Q5_K_M.gguf	Q5_K_M	1.92GB	9.0061 +/- 0.06461
gemma-2-2b-Q5_K_S.gguf	Q5_K_S	1.88GB	9.0096 +/- 0.06451
gemma-2-2b-Q4_K_M.gguf	Q4_K_M	1.71GB	9.2260 +/- 0.06643
gemma-2-2b-Q4_K_S.gguf	Q4_K_S	1.64GB	9.3116 +/- 0.06726
gemma-2-2b-Q3_K_L.gguf	Q3_K_L	1.55GB	9.5683 +/- 0.06909
gemma-2-2b-Q3_K_M.gguf	Q3_K_M	1.46GB	9.7759 +/- 0.07120
gemma-2-2b-Q3_K_S.gguf	Q3_K_S	1.36GB	10.8067 +/- 0.08032
gemma-2-2b-Q2_K.gguf	Q2_K	1.23GB	13.8994 +/- 0.10723

Benchmark Results

Results have been computed using:

hellaswage_val_full

winogrande-debiased-eval

mmlu-validation

Benchmark	Quant type	Metric
WinoGrande (0-shot)	Q8_0	68.3504 +/- 1.3072
WinoGrande (0-shot)	Q4_K_M	67.5612 +/- 1.3157
WinoGrande (0-shot)	Q3_K_M	65.9037 +/- 1.3323
WinoGrande (0-shot)	Q3_K_S	66.6930 +/- 1.3246
WinoGrande (0-shot)	Q2_K	63.2991 +/- 1.3546
HellaSwag (0-shot)	Q8_0	71.25074686
HellaSwag (0-shot)	Q4_K_M	69.95618403
HellaSwag (0-shot)	Q3_K_M	68.00438160
HellaSwag (0-shot)	Q3_K_S	69.95618403
HellaSwag (0-shot)	Q2_K	59.38060147
MMLU (0-shot)	Q8_0	35.5943 +/- 1.2173
MMLU (0-shot)	Q4_K_M	35.5943 +/- 1.2173
MMLU (0-shot)	Q3_K_M	35.2067 +/- 1.2143
MMLU (0-shot)	Q3_K_S	33.9147 +/- 1.2037
MMLU (0-shot)	Q2_K	33.0749 +/- 1.1962

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download fedric95/gemma-2-2b-GGUF --include "gemma-2-2b-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download fedric95/gemma-2-2b-GGUF --include "gemma-2-2b-Q8_0.gguf/*" --local-dir gemma-2-2b-Q8_0

You can either specify a new local-dir (gemma-2-2b-Q8_0) or download them all in place (./)

Reproducibility

https://github.com/ggerganov/llama.cpp/discussions/9020#discussioncomment-10335638

Downloads last month: 1,425

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for fedric95/gemma-2-2b-GGUF

Base model

google/gemma-2-2b

Quantized

(64)

this model