Instructions to use ProCreations/grug-27b-qat-q4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProCreations/grug-27b-qat-q4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ProCreations/grug-27b-qat-q4-gguf",
	filename="grug-27b-qat-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ProCreations/grug-27b-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-27b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-27b-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-27b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ProCreations/grug-27b-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-27b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ProCreations/grug-27b-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-27b-qat-q4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProCreations/grug-27b-qat-q4-gguf:Q4_K_M

Use Docker

docker model run hf.co/ProCreations/grug-27b-qat-q4-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use ProCreations/grug-27b-qat-q4-gguf with Ollama:
```
ollama run hf.co/ProCreations/grug-27b-qat-q4-gguf:Q4_K_M
```

Unsloth Studio

How to use ProCreations/grug-27b-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-27b-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-27b-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-27b-qat-q4-gguf to start chatting

How to use ProCreations/grug-27b-qat-q4-gguf 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-27b-qat-q4-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": "ProCreations/grug-27b-qat-q4-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ProCreations/grug-27b-qat-q4-gguf 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-27b-qat-q4-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 ProCreations/grug-27b-qat-q4-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ProCreations/grug-27b-qat-q4-gguf 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-27b-qat-q4-gguf: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-27b-qat-q4-gguf: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-27b-qat-q4-gguf with Docker Model Runner:
```
docker model run hf.co/ProCreations/grug-27b-qat-q4-gguf:Q4_K_M
```

Lemonade

How to use ProCreations/grug-27b-qat-q4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProCreations/grug-27b-qat-q4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.grug-27b-qat-q4-gguf-Q4_K_M

List all available models

lemonade list

grug-27b-qat-q4-gguf

2026-07-23 refresh: rock now QAT-trained from grug-27b v2.1 weights (deep-think + agent-discipline update). bench table below measured on the v1-era rock vs v1 control - directional guide still; v2.1 rock inherit both the QAT recovery AND the v2.1 brain improvements.

grug put 27b brain in four-bit cave DURING training. brain feel rounding rock before final squish. this not normal quant. this QAT recovery rock, made for Q4 people.

recipe (same as grug-9b-qat, scaled): full-weight QAT on grug-27b, fake int4 asymmetric group-32 with straight-through gradient, ~3M token of grug-think data, Adafactor LR 2e-6, 249 step on one H200. release = 25% QAT move + 75% original anchor (full QAT overcorrect, 9b teach grug this). then fresh BF16 export, quantize ONE time to Q4_K_M.

rocks

file	what
grug-27b-qat-Q4_K_M.gguf	the QAT rock, ~16.5 GB
mmproj-grug-27b-f16.gguf	eye rock (vision), same as main gguf repo

number. same cave, same harness, same llama.cpp build

three rock fight: ordinary Q4 (control), full-QAT Q4, and this rock (25% QAT blend). full-QAT win MBPP big but BREAK tool hand (agent valid 96.6 -> 82.8). grug no ship broken hand. blend rock best overall:

test	control Q4	full-QAT Q4	THIS ROCK
MBPP-60 pass %	81.7	91.7	88.3 (+6.6)
GSM8K-60 %	96.7	95.0	98.3 (+1.6)
agent tool-call valid %	96.6	82.8	96.6 (same)
agent right-tool %	93.1	79.3	89.7 (-3.4)
agent args schema-valid %	100	100	100
identity loop rate %	3.3	0.0	1.7 (halved)
greedy longform loops	1	0	0

QAT feel rounding rock during training -> Q4 squish hurt less. coding and math UP, loop sickness DOWN, tool hand intact. small right-tool dip is the honest trade. grug show all numbers, hide nothing.

if rock act broken

single-token spam ("/" forever etc) = NOT the rock. hybrid DeltaNet brain CANNOT survive llama.cpp context-shift: old builds shift on context overflow and corrupt the recurrent state into token spam. fix:

use RECENT llama.cpp (qwen3_5 support; new builds refuse instead of shift)
agent frontends (OpenCode etc): set -c 16384 or bigger
still broken? re-download rock (verify size) + check backend grug re-test rock after every report: loads clean, zero spam at proper config.

how run

llama-server -m grug-27b-qat-Q4_K_M.gguf --mmproj mmproj-grug-27b-f16.gguf \
  -c 16384 --temp 0.6 --top-p 0.95 --top-k 20

need recent llama.cpp (qwen3_5 arch). grug think live in <think>, short on purpose. tool call use XML format. main model card: grug-27b.

Downloads last month: 1,671

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for ProCreations/grug-27b-qat-q4-gguf

Base model

Qwen/Qwen3.6-27B

Finetuned

ProCreations/grug-27b

Quantized

(8)

this model