Instructions to use RedHatAI/GLM-5.3-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.3-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/GLM-5.3-MXFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/GLM-5.3-MXFP4")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/GLM-5.3-MXFP4", 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-5.3-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/GLM-5.3-MXFP4"
# 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-5.3-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.3-MXFP4

SGLang

How to use RedHatAI/GLM-5.3-MXFP4 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-5.3-MXFP4" \
    --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-5.3-MXFP4",
		"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-5.3-MXFP4" \
        --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-5.3-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.3-MXFP4 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.3-MXFP4
```

GLM-5.3-MXFP4

Model Overview

Model Architecture: GlmMoeDsaForCausalLM
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: FP4
- Activation quantization: FP4
Release Date: 2026-09-15
Version: 1.0
Model Developers: RedHatAI

This model is a quantized version of zai-org/GLM-5.3. It was evaluated on several tasks to assess its quality in comparison to the FP8 checkpoint.

Model Optimizations

This model was obtained by quantizing the weights and activations of zai-org/GLM-5.3 to FP4 (MXFP4, OCP Microscaling) data type, ready for inference with vLLM. Weights use FP4 (e2m1) with group size 32 and power-of-2 (E8M0) scales, while activations use FP4 with dynamic per-group scaling.

This optimization reduces the number of bits per parameter from 8 (FP8) to 4, reducing the disk size and GPU memory requirements by approximately 50%.

Only the weights and activations of the linear operators within transformer blocks are quantized using LLM Compressor.

Deployment

vLLM Serving

vllm serve RedHatAI/GLM-5.3-MXFP4 \
  --kv-cache-dtype fp8_e4m3 \
  --tensor-parallel-size 4 \
  --reasoning-parser glm45 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'

Creation

This model was created by applying LLM Compressor with the MXFP4 scheme in model-free post-training quantization (no calibration data required), exported in compressed-tensors format.

from compressed_tensors.entrypoints.convert import FP8BlockDequantizer

from llmcompressor import model_free_ptq

MODEL_ID = "zai-org/GLM-5.3"
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-MXFP4"

ignore = [
    "re:.*mlp.gate$",
    "re:.*lm_head",
    "re:.*embed_tokens$",
    "re:.*eh_proj$",
    "re:.*self_attn.indexer.weights_proj$",
]

model_free_ptq(
    model_stub=MODEL_ID,
    save_directory=SAVE_DIR,
    scheme="MXFP4",
    ignore=ignore + ["re:.*self_attn.indexer.wk$"],
    converter=FP8BlockDequantizer(ignore=ignore),
    max_workers=2,
    device="cuda:0",
)

Evaluation

This model was evaluated on GSM8K Platinum, IFEval, MATH-500, AIME 2025, and GPQA Diamond using lm-evaluation-harness and lighteval, all served with vLLM (OpenAI-compatible API). Each benchmark was run with 3 seeds (1234, 2345, 3456) and the results averaged; recovery is computed against the FP8 checkpoint on 4 B200s.

Accuracy

Category	Benchmark	zai-org/GLM-5.3 (FP8)	RedHatAI/GLM-5.3-MXFP4	Recovery
Instruction Following	IFEval (prompt-level strict)	91.87%	91.19%	99.26%
Reasoning	GSM8K Platinum (strict-match)	97.60%	96.36%	98.73%
	MATH-500 (pass@1)	95.67%	94.00%	98.26%
	AIME 2025 (pass@1)	98.33%	91.25%	92.80%
	GPQA Diamond (pass@1)	92.42%	89.06%	96.36%

Downloads last month: 2,786

Safetensors

Model size

753B params

Tensor type

BF16

F32

Model tree for RedHatAI/GLM-5.3-MXFP4

Base model

zai-org/GLM-5.3

Quantized

(61)

this model