Instructions to use ProCreations/grug-9b-qat-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProCreations/grug-9b-qat-q4 with Transformers:

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

pipe = pipeline("text-generation", model="ProCreations/grug-9b-qat-q4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ProCreations/grug-9b-qat-q4", dtype="auto")

llama-cpp-python

How to use ProCreations/grug-9b-qat-q4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ProCreations/grug-9b-qat-q4",
	filename="grug-9b-qat-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ProCreations/grug-9b-qat-q4 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-9b-qat-q4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-9b-qat-q4: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-9b-qat-q4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-9b-qat-q4: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-9b-qat-q4:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ProCreations/grug-9b-qat-q4: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-9b-qat-q4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProCreations/grug-9b-qat-q4:Q4_K_M

Use Docker

docker model run hf.co/ProCreations/grug-9b-qat-q4:Q4_K_M

LM Studio
Jan

vLLM

How to use ProCreations/grug-9b-qat-q4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProCreations/grug-9b-qat-q4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProCreations/grug-9b-qat-q4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ProCreations/grug-9b-qat-q4:Q4_K_M

SGLang

How to use ProCreations/grug-9b-qat-q4 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 "ProCreations/grug-9b-qat-q4" \
    --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": "ProCreations/grug-9b-qat-q4",
		"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 "ProCreations/grug-9b-qat-q4" \
        --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": "ProCreations/grug-9b-qat-q4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ProCreations/grug-9b-qat-q4 with Ollama:
```
ollama run hf.co/ProCreations/grug-9b-qat-q4:Q4_K_M
```

Unsloth Studio

How to use ProCreations/grug-9b-qat-q4 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-9b-qat-q4 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-9b-qat-q4 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-9b-qat-q4 to start chatting

How to use ProCreations/grug-9b-qat-q4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/grug-9b-qat-q4: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": "ProCreations/grug-9b-qat-q4:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ProCreations/grug-9b-qat-q4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/grug-9b-qat-q4: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 ProCreations/grug-9b-qat-q4:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ProCreations/grug-9b-qat-q4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/grug-9b-qat-q4:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ProCreations/grug-9b-qat-q4:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use ProCreations/grug-9b-qat-q4 with Docker Model Runner:
```
docker model run hf.co/ProCreations/grug-9b-qat-q4:Q4_K_M
```

Lemonade

How to use ProCreations/grug-9b-qat-q4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProCreations/grug-9b-qat-q4:Q4_K_M

Run and chat with the model

lemonade run user.grug-9b-qat-q4-Q4_K_M

List all available models

lemonade list

grug-9b-qat-q4

grug put 9b bird in four-bit cave during training. bird feel rounding rock before final squish. then grug make real Q4_K_M GGUF. this not normal squish. this QAT recovery.

QAT start from full grug-9b, never train old GGUF, never requantize quant rock. grug fake-quant text linear weight as asymmetric int4, group 32, straight-through gradient. train 3,628,102 token from grug-think. full QAT overcorrected, so grug keep 25% QAT move and 75% original anchor. fixed eval gate choose before release. then export fresh BF16 GGUF and quantize one time to Q4_K_M.

numbers. same cave, same harness

both rocks run same llama.cpp build, greedy, same prompt. control = ordinary grug-9b-Q4_K_M. QAT = this rock.

test	old Q4	QAT Q4	change
HumanEval pass@1 %	75.6	78.0	+2.4
MBPP pass@1 %	75.0	74.0	-1.0
agent tool-call valid %	61.1	88.9	+27.8
agent RIGHT tool %	55.6	77.8	+22.2
agent reasoning present %	100.0	100.0	+0.0
agent reasoning mean word	7.1	5.8	-1.3

grug reasoning format stay same: short grug brain inside <think>...</think>, normal say-word outside, XML tool call untouched. grug measure presence and length above, not merely hope.

grug honest: QAT help model adapt to 4-bit rounding. QAT not magic promise. numbers above say what happen on these probe. hardest real repo task may act different.

rock

grug-9b-qat-Q4_K_M.gguf — about 5.6 GB. good default for 8 GB VRAM cave.

llama-cli -hf ProCreations/grug-9b-qat-q4:Q4_K_M

need recent llama.cpp with qwen3_5 support. thinking live in <think> tag and stay short on purpose. tool call use model XML format.

recipe. grug show work

source: ProCreations/grug-9b
data: ProCreations/grug-think
QAT: full text-stack linear weights, fake int4 asymmetric group size 32
training: 684 optimizer step, 3,628,102 token, LR 2e-06
release blend: 25% QAT checkpoint + 75% original checkpoint. grug show this because honest rock better than secret rock
target export: llama.cpp Q4_K_M, quantized from fresh BF16 conversion
vision tower not in GGUF. text bird only

training config and measured JSON live in this repo. grug no hide recipe behind bush.

Downloads last month: 51

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for ProCreations/grug-9b-qat-q4

Base model

deepreinforce-ai/Ornith-1.0-9B

Finetuned

ProCreations/grug-9b

Quantized

(3)

this model

ProCreations
/

grug-9b-qat-q4

grug-9b-qat-q4

numbers. same cave, same harness

rock

recipe. grug show work

Model tree for ProCreations/grug-9b-qat-q4

Dataset used to train ProCreations/grug-9b-qat-q4