Instructions to use RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK", 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 RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK

SGLang

How to use RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK 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 "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK" \
    --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": "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK",
		"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 "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK" \
        --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": "RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK
```

RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK

GLM5.2 quantized with RTN with MXFP4 MoE and FP8 block activations, and other weights quantized to FP8 block. This model is experimentally supported in vLLM.

Downloads last month: 513

Safetensors

Model size

386B params

Tensor type

BF16

F8_E4M3

F32

Model tree for RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK

Base model

zai-org/GLM-5.2

Quantized

(143)

this model

Evaluation results

datacurve/deep-swe · Deep Swe View evaluation results source leaderboard

46.2
ScaleAI/SWE-bench_Pro · SWE Bench Pro View evaluation results source leaderboard

62.1
Idavidrein/gpqa · Diamond View evaluation results source leaderboard

91.2
cais/hle · Hle
default View evaluation results source

40.5
With tools View evaluation results source

54.7 ^*