Instructions to use morikomorizz/GLM-Collection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morikomorizz/GLM-Collection with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="morikomorizz/GLM-Collection",
	filename="IQ2_M/GLM-5.2-IQ2_M-00001-of-00006.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 morikomorizz/GLM-Collection 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 morikomorizz/GLM-Collection:IQ2_M
# Run inference directly in the terminal:
llama cli -hf morikomorizz/GLM-Collection:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf morikomorizz/GLM-Collection:IQ2_M
# Run inference directly in the terminal:
llama cli -hf morikomorizz/GLM-Collection:IQ2_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 morikomorizz/GLM-Collection:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf morikomorizz/GLM-Collection:IQ2_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 morikomorizz/GLM-Collection:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf morikomorizz/GLM-Collection:IQ2_M

Use Docker

docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M

LM Studio
Jan

vLLM

How to use morikomorizz/GLM-Collection with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M

Ollama
How to use morikomorizz/GLM-Collection with Ollama:
```
ollama run hf.co/morikomorizz/GLM-Collection:IQ2_M
```

Unsloth Studio

How to use morikomorizz/GLM-Collection 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 morikomorizz/GLM-Collection 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 morikomorizz/GLM-Collection to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for morikomorizz/GLM-Collection to start chatting

How to use morikomorizz/GLM-Collection with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf morikomorizz/GLM-Collection:IQ2_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": "morikomorizz/GLM-Collection:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use morikomorizz/GLM-Collection with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf morikomorizz/GLM-Collection:IQ2_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 morikomorizz/GLM-Collection:IQ2_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use morikomorizz/GLM-Collection with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf morikomorizz/GLM-Collection:IQ2_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 "morikomorizz/GLM-Collection:IQ2_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 morikomorizz/GLM-Collection with Docker Model Runner:
```
docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M
```

Lemonade

How to use morikomorizz/GLM-Collection with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull morikomorizz/GLM-Collection:IQ2_M

Run and chat with the model

lemonade run user.GLM-Collection-IQ2_M

List all available models

lemonade list

Overview

Original Model: zai-org/GLM-5.2

This repository contains the GGUF quantized files for zai-org/GLM-5.2.

Version	FFN Exps Gate-Up-Down	Token Embedding	Output Weight	Size
IQ2_M	IQ2_XXS / IQ2_XXS / IQ3_S	Q8_0	Q8_0	262 GB
MixQ5-IQ3_M	IQ3_S / IQ3_S / Q5_K	BF16	BF16	431 GB
MXFP4	MXFP4 / MXFP4 / MXFP4	BF16	BF16	443 GB

Note: The frontmost FFN layers in the first block are all set to Q8_0, while the remaining tensors remain in BF16 and FP32 formats.

The "Garbage In, Garbage Out" Hypothesis

Please note that the Quantization Override (Q8) applied to the very first layers in these custom models is an intentional experiment. The core hypothesis we are testing challenges the "Garbage In, Garbage Out" concept: if the frontmost layers (which capture and process the initial input context) are extensively compressed, will it inevitably trap the model with degraded inputs and result in poor final generations?

And conversely: if the frontmost layers are aggressively preserved, will it allow the model to capture clear and clean inputs, leading to superior final generation results?

Call for Feedback: If you are willing to test these models, please share your performance benchmarks, perplexity scores, or qualitative observations in the Community Discussions or Issues tab. Your field reports are crucial to help determine whether early-layer degradation is a fatal flaw or a manageable trade-off in MoE architectures.

Prompt used:

"Write a single HTML file with a full-page canvas and no libraries. Simulate a realistic side-view of a moving car as the main subject. Keep the car visible in the foreground while the background landscape scrolls continuously to create the feeling that the car is driving forward. Use layered scenery for depth: nearby ground, roadside elements, trees, poles, and distant hills or mountains should move at different speeds for a natural parallax effect. Animate the wheels spinning realistically and add subtle body motion so the car feels connected to the road. Let the environment pass smoothly behind it, with repeating but varied scenery that makes the movement feel believable. Use cinematic lighting and a cohesive sky, such as sunset, dusk, or daylight, to enhance atmosphere. The overall motion should feel calm, immersive, and realistic, with a seamless looping animation."

IQ2_M-Max-Result

Here are the results for IQ2_M on 4 x RTX Pro 6000 :

Thinking Effort: Max
Reasoning Token : 103.879
Output : 10.386

Thinking Max is truly absurd, it spent 2,417 seconds of reasoning on 4 RTX Pro 6000s and burned approximately 100,000 tokens just for its internal thinking. The output is as shown in the preview here.

Download : GLM-5.2-IQ2_M

Downloads last month: 777

GGUF

Model size

754B params

Architecture

glm-dsa

Hardware compatibility

2-bit

3-bit

View +1 variant

Model tree for morikomorizz/GLM-Collection

Base model

zai-org/GLM-5.2

Quantized

(100)

this model