Instructions to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lovedheart/GLM-4.5-Air-GGUF-IQ1_M",
	filename="GLM-4.5-Air-MXFP4_MOE-00001-of-00005.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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

Use Docker

docker model run hf.co/lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

LM Studio
Jan
Ollama
How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with Ollama:
```
ollama run hf.co/lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
```

Unsloth Studio

How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M 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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M 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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lovedheart/GLM-4.5-Air-GGUF-IQ1_M to start chatting

How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

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": "lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

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 lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with Docker Model Runner:
```
docker model run hf.co/lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE
```

Lemonade

How to use lovedheart/GLM-4.5-Air-GGUF-IQ1_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lovedheart/GLM-4.5-Air-GGUF-IQ1_M:MXFP4_MOE

Run and chat with the model

lemonade run user.GLM-4.5-Air-GGUF-IQ1_M-MXFP4_MOE

List all available models

lemonade list

Use unsloth BF16 GGUF to quantize IQ1_M/S. Blk.46 is not being used in llama.cpp therefore the weights of blk.46 are quantized to TQ1_0 to have minimum memory allocation.

Added MXFP4 version:

MXFP4: Embedding, Output are kept with Q6_K. The attn layers use IQ4_XS. All ffn expert layers including shared experts are quantized to SOTA MXFP4.
MXFP4 Max: Embedding, Output and attn layers are kept with Q6_K. First layer uses full precision. The rest of ffn expert layers are quantized to SOTA MXFP4. The shared experts weights keep BF16.

Downloads last month: 19

GGUF

Model size

110B params

Architecture

glm4moe

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

Inference Providers NEW

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

Model tree for lovedheart/GLM-4.5-Air-GGUF-IQ1_M

Base model

zai-org/GLM-4.5-Air

Quantized

(61)

this model

Collection including lovedheart/GLM-4.5-Air-GGUF-IQ1_M

Ultra Low-Bit Thinking Machine

Collection

15 items • Updated Apr 26 • 2