Instructions to use RedHatAI/GLM-5.3-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/GLM-5.3-Flash-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/GLM-5.3-Flash-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RedHatAI/GLM-5.3-Flash-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/GLM-5.3-Flash-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/GLM-5.3-Flash-NVFP4 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-Flash-NVFP4"
# 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-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/GLM-5.3-Flash-NVFP4

SGLang

How to use RedHatAI/GLM-5.3-Flash-NVFP4 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-Flash-NVFP4" \
    --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-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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-Flash-NVFP4" \
        --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-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/GLM-5.3-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/GLM-5.3-Flash-NVFP4
```

GLM-5.3-Flash-NVFP4 / README.md

dsikka

Update README.md

36c184c verified 3 days ago

preview code

Raw

History Blame Contribute Delete

2.15 kB

	---
	base_model:
	- zai-org/GLM-5.3-Flash
	tags:
	- vllm
	- llm-compressor
	- nvfp4
	- fp4
	- glm5_next
	pipeline_tag: image-text-to-text
	library_name: transformers
	---

	# RedHatAI/GLM-5.3-Flash-NVFP4
	This model is a quantized version of [zai-org/GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash).

	# Model Optimizations
	This model was obtained by quantizing the weights of zai-org/GLM-5.3-Flash to NVFP4, ready for inference with vLLM.

	Weights are quantized to FP4 with a group size of 16, and activations are quantized to FP4 with local per-group scaling. Only the weights and activations of the linear operators within transformer blocks are quantized using [LLM Compressor](https://github.com/vllm-project/llm-compressor). Vision tower, embedding, and output head layers are kept in their original precision.

	# vLLM Serving

	```bash
	docker run --gpus all \
	--privileged --ipc=host -p 8000:8000 \
	-v ~/.cache/huggingface:/root/.cache/huggingface \
	-e VLLM_ENGINE_READY_TIMEOUT_S=3600 \
	vllm/vllm-openai:glm53-flash RedHatAI/GLM-5.3-Flash-NVFP4 \
	--tensor-parallel-size 4 \
	--no-enable-flashinfer-autotune \
	--tool-call-parser glm47 \
	--enable-auto-tool-choice \
	--reasoning-parser glm45
	```

	## Enable Speculative Decoding

	```
	docker run --gpus all \
	--privileged --ipc=host -p 8000:8000 \
	-v ~/.cache/huggingface:/root/.cache/huggingface \
	-e VLLM_ENGINE_READY_TIMEOUT_S=3600 \
	-e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
	vllm/vllm-openai:glm53-flash RedHatAI/GLM-5.3-Flash-NVFP4 \
	--tensor-parallel-size 4 \
	--no-enable-flashinfer-autotune \
	--tool-call-parser glm47 \
	--enable-auto-tool-choice \
	--reasoning-parser glm45 \
	--gpu-memory-utilization 0.85 \
	--disable-custom-all-reduce \
	--speculative-config '{"method":"mtp","num_speculative_tokens":5}'
	```

	# Evaluations

	\| Benchmark \| Metric \| Avg Score \|
	\|---\|---\|---\|
	\| GPQA Diamond \| `gpqa_pass@k:k=1` (3 seeds) \| 90.57% \|
	\| AIME25 \| `pass@k:k=1&n=1` (8 seeds) \| 86.67% \|
	\| GSM8K Platinum CoT \| `exact_match,strict-match` (3 seeds) \| 97.74% \|
	\| MATH-500 \| `pass@k:k=1&n=1` (3 seeds) \| 94.87% \|