Instructions to use chimbiwide/GemmaReLe-Q8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chimbiwide/GemmaReLe-Q8-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chimbiwide/GemmaReLe-Q8-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use chimbiwide/GemmaReLe-Q8-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 chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

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 chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

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 chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

Use Docker

docker model run hf.co/chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use chimbiwide/GemmaReLe-Q8-GGUF with Ollama:
```
ollama run hf.co/chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
```

Unsloth Studio

How to use chimbiwide/GemmaReLe-Q8-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 chimbiwide/GemmaReLe-Q8-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 chimbiwide/GemmaReLe-Q8-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chimbiwide/GemmaReLe-Q8-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use chimbiwide/GemmaReLe-Q8-GGUF with Docker Model Runner:
```
docker model run hf.co/chimbiwide/GemmaReLe-Q8-GGUF:Q8_0
```

Lemonade

How to use chimbiwide/GemmaReLe-Q8-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chimbiwide/GemmaReLe-Q8-GGUF:Q8_0

Run and chat with the model

lemonade run user.GemmaReLe-Q8-GGUF-Q8_0

List all available models

lemonade list

GemmaReLe

A test model for ReLe

(btw, we sort of did)

The Q8_0 version of GemmaReLe-float16.

The Gemma3NPC series were meant to be a sort of general purposed video game RP model.

This time, using the chimbiwide/ReLe_Synthetic_v1_json, we trained a model to specifically act as ReLe.

For more information on Who is ReLe?, visit the dataset README.

Warning: This is NOT a general purpose model. Performance requires further testing.

Check out our training notebook here

Training parameters compared to `Gemma3NPC-it`

Parameter	Gemma3NPC-it	Gemma3NPC-it-beta
Learning Rate	2e-5	2.5e-5 (+25%)
Warmup Steps	800	100
gradient clipping	0.4	1.0

Graph of the Step Training Loss, saved every 10 steps:

Fun Discovery

For the first time ever, we encountered a whole number trianing loss.

Downloads last month: 10

GGUF

Model size

7B params

Architecture

gemma3n

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for chimbiwide/GemmaReLe-Q8-GGUF

Base model

chimbiwide/GemmaReLe

Quantized

(2)

this model

Dataset used to train chimbiwide/GemmaReLe-Q8-GGUF

Collection including chimbiwide/GemmaReLe-Q8-GGUF

GemmaReLe

Collection

A collection of all the GemmaReLe models, a special version of Gemma3NPC, made specifically for ReLe • 3 items • Updated Feb 27

GemmaReLe

A test model for ReLe

Training parameters compared to Gemma3NPC-it

Graph of the Step Training Loss, saved every 10 steps:

Fun Discovery

Model tree for chimbiwide/GemmaReLe-Q8-GGUF

Dataset used to train chimbiwide/GemmaReLe-Q8-GGUF

Collection including chimbiwide/GemmaReLe-Q8-GGUF

Training parameters compared to `Gemma3NPC-it`