Instructions to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF",
	filename="granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

Use Docker

docker model run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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": "glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

Ollama
How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with Ollama:
```
ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
```

Unsloth Studio

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF to start chatting

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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": "glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 "glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-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 glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with Docker Model Runner:
```
docker model run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M
```

Lemonade

How to use glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF-Q4_K_M

List all available models

lemonade list

granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF

GGUF quantized versions of granite-4.0-h-1b-DISTILL-glm-4.7-think

Available Formats

Filename	Size	Quant Type
granite-4.0-h-1b-DISTILL-glm-4.7-think-f16.gguf	2.73 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-F16
granite-4.0-h-1b-DISTILL-glm-4.7-think-q2_k.gguf	0.55 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q2_K
granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_l.gguf	0.71 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_L
granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_m.gguf	0.68 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_M
granite-4.0-h-1b-DISTILL-glm-4.7-think-q3_k_s.gguf	0.65 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q3_K_S
granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_0.gguf	0.81 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_0
granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_1.gguf	0.88 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_1
granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_m.gguf	0.84 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_K_M
granite-4.0-h-1b-DISTILL-glm-4.7-think-q4_k_s.gguf	0.81 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q4_K_S
granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_0.gguf	0.96 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_0
granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_1.gguf	1.04 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_1
granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_m.gguf	0.98 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_K_M
granite-4.0-h-1b-DISTILL-glm-4.7-think-q5_k_s.gguf	0.96 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q5_K_S
granite-4.0-h-1b-DISTILL-glm-4.7-think-q6_k.gguf	1.12 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q6_K
granite-4.0-h-1b-DISTILL-glm-4.7-think-q8_0.gguf	1.45 GB	GRANITE-4.0-H-1B-DISTILL-GLM-4.7-THINK-Q8_0

Quick Start

Ollama

# Use Q4_K_M (recommended)
ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q4_K_M

# Or other quantizations
ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q8_0
ollama run hf.co/glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF:Q2_K

llama.cpp

# Download and run
llama-cli --hf-repo glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF --hf-file granite-4.0-h-1b-distill-glm-4.7-think-q4_k_m.gguf -p "Hello, how are you?"

# With server
llama-server --hf-repo glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF --hf-file granite-4.0-h-1b-distill-glm-4.7-think-q4_k_m.gguf -c 2048

LM Studio / GPT4All

Download the .gguf file of your choice and load it in your application.

Quantization Details

Type	Bits	Use Case
Q2_K	2	Extreme compression, low quality
Q3_K_M	3	Very compressed
Q4_K_M	4	Recommended - Best size/quality
Q5_K_M	5	High quality
Q6_K	6	Very high quality
Q8_0	8	Near lossless
F16	16	Original precision

Original Model

This is the quantized version of granite-4.0-h-1b-DISTILL-glm-4.7-think

Base Model: ibm-granite/granite-4.0-h-1b
Fine-tuning Dataset: TeichAI/glm-4.7-2000x
Training Loss: 0.6364

Downloads last month: 273

GGUF

Model size

1B params

Architecture

granitehybrid

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF

Base model

ibm-granite/granite-4.0-h-1b-base

Finetuned

ibm-granite/granite-4.0-h-1b

Finetuned

glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think

Quantized

(1)

this model