Instructions to use 0xSero/GLM-5-381B-GGUF-IQ2_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M 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 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
# Run inference directly in the terminal:
llama cli -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
# Run inference directly in the terminal:
llama cli -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-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 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-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 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Use Docker

docker model run hf.co/0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

LM Studio
Jan

vLLM

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/GLM-5-381B-GGUF-IQ2_M"
# 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-5-381B-GGUF-IQ2_M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Ollama
How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with Ollama:
```
ollama run hf.co/0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
```
Unsloth Desktop

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-5-381B-GGUF-IQ2_M:UD-IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with Docker Model Runner:
```
docker model run hf.co/0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M
```

Lemonade

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Run and chat with the model

lemonade run user.GLM-5-381B-GGUF-IQ2_M-UD-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-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 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 0xSero/GLM-5-381B-GGUF-IQ2_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xSero/GLM-5-381B-GGUF-IQ2_M:UD-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 "0xSero/GLM-5-381B-GGUF-IQ2_M:UD-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"

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

GLM-5-381B-GGUF-IQ2_M

GGUF quantization of zai-org/GLM-5.

At a glance


Base model	zai-org/GLM-5
Format	GGUF
Total params	381B
Active / token	—
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	130 GB

Which variant should I pick?

Variant	Format	Link
`GLM-5-381B`	BF16	link
`GLM-5-381B-GGUF-BF16`	GGUF	link
`GLM-5-381B-GGUF-IQ2_M` (this)	GGUF	link
`GLM-5-381B-GGUF-IQ2_XXS`	GGUF	link
`GLM-5-381B-GGUF-Q3_K_M`	GGUF	link
`GLM-5-381B-W3A16`	W3A16	link
`glm5-reap-observations`	BF16	link

Expert-pruned GLM-5 (744B -> ~372B params, 256 -> 128 routed experts) quantized to dynamic IQ2_M (2.72 BPW) using importance-matrix calibration. Fits in ~125-130 GB VRAM with KV cache room.

Benchmark Results (Pilot, 10 samples/category)

Category	Q3_K_M (170GB)	UD-IQ2_M (121GB)	UD-IQ2_XXS (97GB)
Math (GSM8K)	8/10 (80%)	6/10 (60%)	2/10 (20%)
Reasoning (BBH)	8/10 (80%)	7/10 (70%)	4/10 (40%)
Coding (HumanEval)	9/10 (90%)	8/10 (80%)	7/10 (70%)
Agentic (SWE-bench)	10/10 (100%)	10/10 (100%)	10/10 (100%)
Terminal-bench	9/10 (90%)	9/10 (90%)	10/10 (100%)
Overall	44/50 (88%)	40/50 (80%)	33/50 (66%)

Fidelity to Q3_K_M: 91% (40/44). Math and reasoning are most affected by quantization.

Model Details

Property	Value
Base model	zai-org/GLM-5 (744B, 256 routed experts)
Pruning	REAP saliency pruning, 50% expert removal (256 -> 128 experts)
Quantization	Dynamic IQ2_M with imatrix (2.72 BPW)
Size	~121 GB
Architecture	GlmMoeDsaForCausalLM (MLA + MoE + DSA)
Context	202,752 tokens
Active params	~20B per token (8 of 128 experts)

Dynamic Quantization Strategy

Component	Quant Type	Rationale
`output.weight`	Q5_K	Critical for logit quality
`token_embd.weight`	Q4_K	Important for input representation
Dense FFN (first 3 layers)	Q5_K	No MoE; all traffic flows through
MLA attention projections	Q4_K	Coherence-critical
MLA key projection (`attn_k_b`)	Q5_K	Higher precision for keys
DSA indexer (`indexer.*`)	Q5_K	Critical for attention routing
Shared experts (`ffn_*_shexp`)	Q4_K-Q5_K	Always active
Last MoE layer (blk.77)	Q3_K	Final representation
Routed MoE experts (bulk)	IQ2_M	Main savings; imatrix-calibrated

Usage

huggingface-cli download 0xSero/GLM-5-381B-GGUF-IQ2_M --local-dir ./model

./llama-server \
    --model ./model/GLM-5-REAP-50pct-UD-IQ2_M.gguf \
    --ctx-size 8192 \
    --n-gpu-layers 99 \
    --port 8080 \
    --reasoning-budget 2048

Requires ~125 GB VRAM (model + KV cache at 8K context). Fits on 2x H100 80GB or 1x B200 192GB.

All Variants

Variant	BPW	Size	Parse Rate	Repo
BF16	16.00	711 GB	N/A	BF16-GGUF
Q3_K_M	3.82	170 GB	88%	Q3_K_M-GGUF
UD-IQ2_M (this)	2.72	121 GB	80%	this repo
UD-IQ2_XXS	2.19	97 GB	66%	UD-IQ2_XXS-GGUF

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-5-381B-GGUF-IQ2_M

Base model

zai-org/GLM-5

Quantized

(19)

this model

Collection including 0xSero/GLM-5-381B-GGUF-IQ2_M

GLM — REAP

Collection

REAP-pruned & quantized GLM-4.x / 5 / 5.1 (+ Flash fine-tunes). • 34 items • Updated 13 days ago • 2

Paper for 0xSero/GLM-5-381B-GGUF-IQ2_M

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

Paper • 2510.13999 • Published Oct 15, 2025 • 23

0xSero
/

GLM-5-381B-GGUF-IQ2_M

GLM-5-381B-GGUF-IQ2_M

At a glance

Which variant should I pick?

Benchmark Results (Pilot, 10 samples/category)

Model Details

Dynamic Quantization Strategy

Usage

All Variants

License & citation

Sponsors

Model tree for 0xSero/GLM-5-381B-GGUF-IQ2_M

Collection including 0xSero/GLM-5-381B-GGUF-IQ2_M

GLM — REAP

Paper for 0xSero/GLM-5-381B-GGUF-IQ2_M

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