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

Libraries

How to use yasu-oh/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="yasu-oh/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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yasu-oh/GLM-5.3-Flash-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("yasu-oh/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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yasu-oh/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 "yasu-oh/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": "yasu-oh/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/yasu-oh/GLM-5.3-Flash-NVFP4

SGLang

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

GLM-5.3-Flash-NVFP4

An NVFP4-quantized version of zai-org/GLM-5.3-Flash.

This model was independently quantized to NVFP4 W4A4 using LLM Compressor and saved in the compressed-tensors format.

Model Details

Base model: zai-org/GLM-5.3-Flash
Architecture: Glm5NextForConditionalGeneration
Quantization: NVFP4 W4A4
Serialization format: nvfp4-pack-quantized
Compression backend: compressed-tensors
Calibration samples: 1,024
Maximum calibration sequence length: 4,096 tokens

Calibration Data

The following datasets were used for calibration:

The calibration dataset consists of:

512 general multilingual instruction samples from Aya
512 reasoning and tool-use conversation samples from Hermes

Quantization Configuration

default_stage:
  default_modifiers:
    GPTQModifier:
      config_groups:
        group_0:
          targets: ['re:.*mlp\.experts\..*(gate|up|down)_proj$']
          weights:
            num_bits: 4
            type: float
            symmetric: true
            group_size: 16
            strategy: tensor_group
            dynamic: false
            actorder: static
            scale_dtype: torch.float8_e4m3fn
            observer: nvfp4_expanded_imatrix
            observer_kwargs: {strict: true}
          input_activations: {num_bits: 4, type: float, symmetric: true, group_size: 16, strategy: tensor_group,
            dynamic: local, scale_dtype: torch.float8_e4m3fn, observer: static_minmax}
          output_activations: null
          format: null
      targets: [Linear]
      ignore: ['re:.*visual.*', lm_head, 're:.*mlp\.gate$', 're:.*self_attn\.indexer\..*']
      bypass_divisibility_checks: false
      requires_calibration_data: true
      block_size: 128
      dampening_frac: 0.01
      actorder: static
      batched_quantization: auto

Reproducibility

The quantization code and calibration preprocessing are available at:

glm-5.3-flash-nvfp4-quantization

The quantization run used:

transformers:        5.22.2
llmcompressor:       0.15.1a20261106
compressed-tensors:  0.20.2a20261103

Downloads last month: 43

Safetensors

Model size

321B params

Tensor type

F32

BF16

Model tree for yasu-oh/GLM-5.3-Flash-NVFP4

Base model

zai-org/GLM-5.3-Flash

Quantized

(240)

this model

yasu-oh
/

GLM-5.3-Flash-NVFP4