Instructions to use 0xSero/GLM-5.1-555B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/GLM-5.1-555B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="0xSero/GLM-5.1-555B-GGUF",
	filename="glm51-555b-reap-Q4_K_M-protected-split.gguf-00001-of-00009.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-5.1-555B-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-5.1-555B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 0xSero/GLM-5.1-555B-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-5.1-555B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 0xSero/GLM-5.1-555B-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-5.1-555B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 0xSero/GLM-5.1-555B-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-5.1-555B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xSero/GLM-5.1-555B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/0xSero/GLM-5.1-555B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use 0xSero/GLM-5.1-555B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/GLM-5.1-555B-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-5.1-555B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/GLM-5.1-555B-GGUF:Q4_K_M

Ollama
How to use 0xSero/GLM-5.1-555B-GGUF with Ollama:
```
ollama run hf.co/0xSero/GLM-5.1-555B-GGUF:Q4_K_M
```

Unsloth Studio

How to use 0xSero/GLM-5.1-555B-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-5.1-555B-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-5.1-555B-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-5.1-555B-GGUF to start chatting

How to use 0xSero/GLM-5.1-555B-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-5.1-555B-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-5.1-555B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 0xSero/GLM-5.1-555B-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-5.1-555B-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-5.1-555B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use 0xSero/GLM-5.1-555B-GGUF with Docker Model Runner:
```
docker model run hf.co/0xSero/GLM-5.1-555B-GGUF:Q4_K_M
```

Lemonade

How to use 0xSero/GLM-5.1-555B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xSero/GLM-5.1-555B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GLM-5.1-555B-GGUF-Q4_K_M

List all available models

lemonade list

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

GLM-5.1-555B-GGUF

GGUF quantization of zai-org/GLM-5.1.

At a glance


Base model	zai-org/GLM-5.1
Format	GGUF
Total params	555B
Active / token	14B
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	348 GB

Which variant should I pick?

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

This is a Q4_K_M quantized GGUF of the 25% expert-pruned zai-org/GLM-5.1 using REAP (Relative Expert Activation Pruning).

Property	Value
Base model	`zai-org/GLM-5.1` (744B MoE, 256 experts/layer)
Architecture	`GlmMoeDsaForCausalLM` (MoE + Dynamic Sparse Attention)
Routed experts	256 → 192 (25% removed, 64 per layer)
Active params/token	~14B (top-8 routing preserved)
Quantization	Q4_K_M with Q8_0 protection for attention, router, shared expert, dense layers
GGUF size	325 GB (single file)
BF16 source	`0xSero/GLM-5.1-555B`

Benchmark Results (inference mode, temp=0.8)

Suite	Metric	Result	Repetition Loops
Terminal-Bench (50)	Proxy Pass	44/50 (88%)	0/50
SWE-bench Pro (50)	Proxy Pass	33/50 (66%)	0/50
GSM8K (50)	Correct	30/50 (60%)	0/50
HLE (50)	Correct	9/50 (18%)	0/50

Zero repetition loops across 220 benchmark probes. This model completely eliminates the repetition degeneration that affected the more aggressively pruned 40% variant.

Degeneration Fuzz Test (45 probes)

Category	Result
Code generation (15)	2/15 borderline (btree, sql_schema)
Structured output (4)	1/4 borderline (api_spec)
Reasoning (4)	0/4
Creative writing (4)	0/4
Math (2)	0/2
Domain knowledge (3)	0/3
Patch generation (3)	0/3
Overall	4/45 (8.9%) — all borderline

Why 25% instead of 40%?

The 40% pruned variant (444B, 154 experts/layer) suffered from repetition loops in ~29% of code/structured generation tasks. Root cause analysis showed the degeneration rate is determined by pruning aggressiveness — removing 40% of experts left too few for the model to maintain coherent long-form output. The 25% prune retains 192/256 experts, providing enough expert diversity for stable generation at all sequence lengths.

How to Use

# Requires llama.cpp with CUDA support
llama-server \
  -m glm51-555b-reap-Q4_K_M-protected.gguf \
  -ngl 99 -c 131072 -np 1 --alias glm51-q4 \
  --host 127.0.0.1 --port 8011 \
  --jinja --reasoning on --reasoning-format deepseek

Requires ~80-90 GiB VRAM per GPU across 4 GPUs, or ~325 GiB total.

Quantization Details

Protected at Q8_0 (NOT quantized to Q4):

Router gate weights + bias
DSA indexer weights
All attention projections + norms
Shared expert (gate, up, down)
Dense layers (first 3 layers)
Token embeddings + output head

Quantized to Q4_K / Q6_K:

Routed expert projections (gate, up → Q4_K; down → Q6_K)

Related Models

Model	Prune %	Experts	Status
`0xSero/GLM-5.1-555B`	25%	192/256	BF16 source for this GGUF
`0xSero/GLM-5.1-444B`	40%	154/256	Has repetition issues — use 25% instead
`0xSero/GLM-5.1-444B-GGUF`	40%	154/256	BROKEN — repetition loops, deprecated

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}
}