Instructions to use RichardErkhov/unsloth_-_gemma-2b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/unsloth_-_gemma-2b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/unsloth_-_gemma-2b-gguf",
	filename="gemma-2b.IQ3_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/unsloth_-_gemma-2b-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
```

Unsloth Studio new

How to use RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-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 RichardErkhov/unsloth_-_gemma-2b-gguf to start chatting

Docker Model Runner
How to use RichardErkhov/unsloth_-_gemma-2b-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/unsloth_-_gemma-2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/unsloth_-_gemma-2b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.unsloth_-_gemma-2b-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2b - GGUF

Model creator: https://huggingface.co/unsloth/
Original model: https://huggingface.co/unsloth/gemma-2b/

Name	Quant method	Size
gemma-2b.Q2_K.gguf	Q2_K	1.08GB
gemma-2b.IQ3_XS.gguf	IQ3_XS	1.16GB
gemma-2b.IQ3_S.gguf	IQ3_S	1.2GB
gemma-2b.Q3_K_S.gguf	Q3_K_S	1.2GB
gemma-2b.IQ3_M.gguf	IQ3_M	1.22GB
gemma-2b.Q3_K.gguf	Q3_K	1.29GB
gemma-2b.Q3_K_M.gguf	Q3_K_M	1.29GB
gemma-2b.Q3_K_L.gguf	Q3_K_L	1.36GB
gemma-2b.IQ4_XS.gguf	IQ4_XS	1.4GB
gemma-2b.Q4_0.gguf	Q4_0	1.44GB
gemma-2b.IQ4_NL.gguf	IQ4_NL	1.45GB
gemma-2b.Q4_K_S.gguf	Q4_K_S	1.45GB
gemma-2b.Q4_K.gguf	Q4_K	1.52GB
gemma-2b.Q4_K_M.gguf	Q4_K_M	1.52GB
gemma-2b.Q4_1.gguf	Q4_1	1.56GB
gemma-2b.Q5_0.gguf	Q5_0	1.68GB
gemma-2b.Q5_K_S.gguf	Q5_K_S	1.68GB
gemma-2b.Q5_K.gguf	Q5_K	1.71GB
gemma-2b.Q5_K_M.gguf	Q5_K_M	1.71GB
gemma-2b.Q5_1.gguf	Q5_1	1.79GB
gemma-2b.Q6_K.gguf	Q6_K	1.92GB
gemma-2b.Q8_0.gguf	Q8_0	2.49GB

Original model description:

language: - en license: apache-2.0 library_name: transformers tags: - unsloth - transformers - gemma - gemma-2b

Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Gemma 7b	▶️ Start on Colab	2.4x faster	58% less
Mistral 7b	▶️ Start on Colab	2.2x faster	62% less
Llama-2 7b	▶️ Start on Colab	2.2x faster	43% less
TinyLlama	▶️ Start on Colab	3.9x faster	74% less
CodeLlama 34b A100	▶️ Start on Colab	1.9x faster	27% less
Mistral 7b 1xT4	▶️ Start on Kaggle	5x faster*	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

Downloads last month: 107

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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