Instructions to use MuVeraAI/glm-5-381-reap-w3a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuVeraAI/glm-5-381-reap-w3a16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MuVeraAI/glm-5-381-reap-w3a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MuVeraAI/glm-5-381-reap-w3a16")
model = AutoModelForCausalLM.from_pretrained("MuVeraAI/glm-5-381-reap-w3a16", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MuVeraAI/glm-5-381-reap-w3a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuVeraAI/glm-5-381-reap-w3a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuVeraAI/glm-5-381-reap-w3a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuVeraAI/glm-5-381-reap-w3a16

SGLang

How to use MuVeraAI/glm-5-381-reap-w3a16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MuVeraAI/glm-5-381-reap-w3a16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuVeraAI/glm-5-381-reap-w3a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MuVeraAI/glm-5-381-reap-w3a16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuVeraAI/glm-5-381-reap-w3a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MuVeraAI/glm-5-381-reap-w3a16 with Docker Model Runner:
```
docker model run hf.co/MuVeraAI/glm-5-381-reap-w3a16
```

Support this work: donate.sybilsolutions.ai

REAP surfaces: GLM | MiniMax | Qwen | Gemma | Paper | Code | PR17 | Cerebras Collection

glm-5-381-reap-w3a16

This repository contains the W3A16 AutoRound quantization of the 50% REAP-pruned GLM-5 checkpoint.

Checkpoint

Base family: GLM-5
Architecture: GlmMoeDsaForCausalLM
Total parameters: 381,464,351,232
Source prune: refusal_contrast_reap, compression ratio 0.50, seed 42, router renormalization true
Quantization method: AutoRound
Quantization scheme: W3A16
Group size: 128
Calibration dataset: NeelNanda/pile-10k
Calibration samples: 128
Sequence length: 1024
Iterations per block: 50

Output

Saved model shards: 29
Quantized tensors: 29,571 / 29,659
Quantization config file: quantization_config.json

Intentionally Unquantized

lm_head
model.layers.[0-2].mlp.down_proj
model.layers.[0-2].mlp.gate_proj
model.layers.[0-2].mlp.up_proj
model.layers.[0-77].self_attn.indexer.weights_proj

Provenance

Quantized artifact path: /data0/external_research/glm5-autoround/full/glm5-reap-50pct-w3a16-pile10k-20260405T182123Z/output/layerwise_refusal_contrast_reap-renorm_true-seed_42-0.50-w3g128
Quantization log: /data0/external_research/glm5-autoround/full/glm5-reap-50pct-w3a16-pile10k-20260405T182123Z/quant.log

Notes

The source checkpoint for this quantization is the BF16 50% REAP GLM-5 artifact.
AutoRound reported total tuning time 4549.26s.

Model tree for MuVeraAI/glm-5-381-reap-w3a16

Base model

zai-org/GLM-5

Quantized

(20)

this model

Paper for MuVeraAI/glm-5-381-reap-w3a16

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

Paper • 2510.13999 • Published Oct 15, 2025 • 20

MuVeraAI
/

glm-5-381-reap-w3a16