Instructions to use ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-3b-qat-q4-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProCreations/grug-3b-qat-q4-gguf:Q4_K_M

Use Docker

docker model run hf.co/ProCreations/grug-3b-qat-q4-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use ProCreations/grug-3b-qat-q4-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProCreations/grug-3b-qat-q4-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProCreations/grug-3b-qat-q4-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ProCreations/grug-3b-qat-q4-gguf:Q4_K_M

Ollama
How to use ProCreations/grug-3b-qat-q4-gguf with Ollama:
```
ollama run hf.co/ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
```

Unsloth Studio

How to use ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-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 ProCreations/grug-3b-qat-q4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ProCreations/grug-3b-qat-q4-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use ProCreations/grug-3b-qat-q4-gguf with Docker Model Runner:
```
docker model run hf.co/ProCreations/grug-3b-qat-q4-gguf:Q4_K_M
```

Lemonade

How to use ProCreations/grug-3b-qat-q4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProCreations/grug-3b-qat-q4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.grug-3b-qat-q4-gguf-Q4_K_M

List all available models

lemonade list

grug-3b-qat-q4-gguf

q4 that survive the squeeze.

normal q4 round the weight after training and hope. this one train WITH the rounding: every linear weight fake-quantized to asymmetric int4 (group 32) on each forward, straight-through gradient update the bf16 weight underneath. model learn weight that still work after Q4_K_M round them. same recipe as grug-9b-qat and grug-27b-qat.

trained on same data as ProCreations/grug-3b, so grug dialect and adaptive think length come through intact.

file	size	note
grug-3b-qat-q4-Q4_K_M.gguf	2.57 GB	the point of this repo
grug-3b-qat-q4-f16.gguf	8.34 GB	qat weights unquantized, roll your own quant

use the Q4_K_M one. plain (non-qat) quants live here.

llama.cpp support

Nanbeige4.2 not in upstream llama.cpp yet (issue #26086). Nanbeige team PR #25994 add it - weight-shared depth loop, num_loops=2. until merge, build from that branch:

git clone --depth 1 --branch nanbeige42 https://github.com/Nanbeige/llama.cpp
cd llama.cpp && cmake -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build -j
./build/bin/llama-cli -m grug-3b-Q4_K_M.gguf -p "What is 12 times 12?"

these gguf converted and load-probed with that branch.