Instructions to use 0xSero/GLM-5.1-444B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/GLM-5.1-444B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="0xSero/GLM-5.1-444B-GGUF",
	filename="glm51-444b-reap-Q4_K_M-protected-00001-of-00019.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 0xSero/GLM-5.1-444B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 0xSero/GLM-5.1-444B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 0xSero/GLM-5.1-444B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 0xSero/GLM-5.1-444B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 0xSero/GLM-5.1-444B-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 0xSero/GLM-5.1-444B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 0xSero/GLM-5.1-444B-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 0xSero/GLM-5.1-444B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xSero/GLM-5.1-444B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/0xSero/GLM-5.1-444B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use 0xSero/GLM-5.1-444B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/GLM-5.1-444B-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": "0xSero/GLM-5.1-444B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/GLM-5.1-444B-GGUF:Q4_K_M

Ollama
How to use 0xSero/GLM-5.1-444B-GGUF with Ollama:
```
ollama run hf.co/0xSero/GLM-5.1-444B-GGUF:Q4_K_M
```

Unsloth Studio

How to use 0xSero/GLM-5.1-444B-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 0xSero/GLM-5.1-444B-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 0xSero/GLM-5.1-444B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 0xSero/GLM-5.1-444B-GGUF to start chatting

How to use 0xSero/GLM-5.1-444B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 0xSero/GLM-5.1-444B-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": "0xSero/GLM-5.1-444B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 0xSero/GLM-5.1-444B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 0xSero/GLM-5.1-444B-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 0xSero/GLM-5.1-444B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use 0xSero/GLM-5.1-444B-GGUF with Docker Model Runner:
```
docker model run hf.co/0xSero/GLM-5.1-444B-GGUF:Q4_K_M
```

Lemonade

How to use 0xSero/GLM-5.1-444B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xSero/GLM-5.1-444B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GLM-5.1-444B-GGUF-Q4_K_M

List all available models

lemonade list

Support this work → · X · GitHub · REAP paper · Cerebras REAP

GLM-5.1-444B-GGUF

GGUF quantization of zai-org/GLM-5.1.

At a glance


Base model	zai-org/GLM-5.1
Format	GGUF
Total params	444B
Active / token	14B
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	283 GB

Which variant should I pick?

Variant	Format	Link
`GLM-5.1-444B`	BF16	link
`GLM-5.1-444B-GGUF` (this)	GGUF	link
`GLM-5.1-478B-NVFP4`	NVFP4	link
`GLM-5.1-555B`	BF16	link
`GLM-5.1-555B-GGUF`	GGUF	link
`GLM-5.1-555B-NVFP4`	NVFP4	link
`GLM-5.1-555B-W4A16`	W4A16	link

This model has repetition degeneration. Use the 25% pruned version instead.

Use this instead: 0xSero/GLM-5.1-555B-GGUF

What is wrong with this model?

This is a Q4_K_M GGUF of the 40% expert-pruned GLM-5.1 (154/256 experts retained). It suffers from repetition degeneration - the model enters infinite loops when generating code, structured output, or any long-form content requiring syntactic templates.

Measured degeneration rates:

29% overall (13/45 probes degenerate in fuzz testing)
40% of code generation tasks loop (red-black trees, chess engines, regex, B-trees)
75% of structured output tasks loop (comparison tables, API specs, enum lists)
18% of Terminal-Bench probes loop (9/50)
30% of SWE-bench Pro probes loop (12/40)

Root cause:

Removing 40% of experts (102 per layer) exceeds the model's tolerance for expert pruning. The remaining 154 experts cannot cover the full routing distribution needed for coherent long-form generation. The degeneration compounds over sequence length - short outputs (<512 tokens) work fine, but anything over ~600-1000 words risks entering a repetition loop.

The fix:

The 25% pruned variant (192/256 experts, 555B) completely eliminates repetition loops while maintaining competitive quality:

0/220 benchmark probes had repetition loops
Terminal-Bench: 88% proxy pass rate
SWE-Pro: 66% proxy pass rate

Use 0xSero/GLM-5.1-555B-GGUF instead.

License & citation

License inherited from the base model.

@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}

Model tree for 0xSero/GLM-5.1-444B-GGUF

Base model

zai-org/GLM-5.1

Quantized

(41)

this model

Space using 0xSero/GLM-5.1-444B-GGUF 1

Collection including 0xSero/GLM-5.1-444B-GGUF

GLM — REAP

Collection

REAP-pruned & quantized GLM-4.x / 5 / 5.1 (+ Flash fine-tunes). • 17 items • Updated 17 days ago

Paper for 0xSero/GLM-5.1-444B-GGUF

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 20

0xSero
/

GLM-5.1-444B-GGUF