Instructions to use SL-AI/GRaPE-Mini-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="SL-AI/GRaPE-Mini-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SL-AI/GRaPE-Mini-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SL-AI/GRaPE-Mini-Instruct-GGUF",
	filename="grape_mini_instruct.bf16.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 SL-AI/GRaPE-Mini-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SL-AI/GRaPE-Mini-Instruct-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 SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SL-AI/GRaPE-Mini-Instruct-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 SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SL-AI/GRaPE-Mini-Instruct-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 SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SL-AI/GRaPE-Mini-Instruct-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": "SL-AI/GRaPE-Mini-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

SGLang

How to use SL-AI/GRaPE-Mini-Instruct-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 "SL-AI/GRaPE-Mini-Instruct-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": "SL-AI/GRaPE-Mini-Instruct-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 "SL-AI/GRaPE-Mini-Instruct-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": "SL-AI/GRaPE-Mini-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Ollama:
```
ollama run hf.co/SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use SL-AI/GRaPE-Mini-Instruct-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 SL-AI/GRaPE-Mini-Instruct-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 SL-AI/GRaPE-Mini-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SL-AI/GRaPE-Mini-Instruct-GGUF to start chatting

Pi new

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use SL-AI/GRaPE-Mini-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SL-AI/GRaPE-Mini-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GRaPE-Mini-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

The General Reasoning Agent (for) Project Exploration

The GRaPE Family

Attribute	Size	Modalities	Domain
GRaPE Flash	7B A1B	Text in, Text out	High-Speed Applications
GRaPE Mini (Instruct)	3B	Text + Image + Video in, Text out	On-Device Deployment
GRaPE Nano	700M	Text in, Text out	Extreme Edge Deployment

Capabilities

The GRaPE Family was trained on about 14 billion tokens of data after pre-training. About half was code related tasks, with the rest being heavy on STEAM. Ensuring the model has a sound logical basis.

GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.

How to Run

I recommend using LM Studio for running GRaPE Models, and have generally found these sampling parameters to work best:

Name	Value
Temperature	0.6
Top K Sampling	40
Repeat Penalty	1
Top P Sampling	0.85
Min P Sampling	0.05

Uses of GRaPE Mini Right Now

GRaPE Mini was foundational to the existence of Andy-4.1, a model trained to play Minecraft. This was a demo proving the efficiency and power this architecture can make.

GRaPE Mini as a Model

GRaPE Mini Instruct is a version of GRaPE Mini that was not trained on any data regarding reasoning tasks. It was the foundation which allowed for the unique architecture shown in GRaPE Mini to truly be expressed.

GRaPE Mini Instruct exists also as a way for lower compute devices to run GRaPE Models.

Architecture

GRaPE Flash: Built on the OlMoE Architecture, allowing for incredibly fast speeds where it matters. Allows for retaining factual information, but lacks in logical tasks.
GRaPE Mini: Built on the Qwen3 VL Architecture, allowing for edge case deployments, where logic cannot be sacrificed.
GRaPE Nano: Built on the LFM 2 Architecture, allowing for the fastest speed, and the most knowledge in the tiniest package.

Notes

The GRaPE Family started all the way back in August of 2025, meaning these models are severely out of date on architecture, and training data.

GRaPE 2 will come sooner than the GRaPE 1 family had, and will show multiple improvements.

There are no benchmarks for GRaPE 1 Models due to the costly nature of running them, as well as prioritization of newer models.

Updates for GRaPE 2 models will be posted here on Huggingface, as well as Skinnertopia

Demos for select GRaPE Models can be found here: https://github.com/Sweaterdog/GRaPE-Demos

Downloads last month: 61

GGUF

Model size

3B params

Architecture

qwen3vl

Hardware compatibility

2-bit

4-bit

6-bit

8-bit

16-bit

Collection including SL-AI/GRaPE-Mini-Instruct-GGUF

GRaPE

Collection

The first generation of the General Reasoning Agent for Project Exploration. Designed by SLAI to be helpful, and do what you need it to without fail. • 9 items • Updated Mar 19 • 2