Instructions to use zai-org/GLM-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-OCR with Transformers:

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

pipe = pipeline("image-text-to-text", model="zai-org/GLM-OCR")
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 AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-OCR")
model = AutoModelForImageTextToText.from_pretrained("zai-org/GLM-OCR")
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 = 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/GLM-OCR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-OCR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-OCR",
		"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/zai-org/GLM-OCR

SGLang

How to use zai-org/GLM-OCR 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 "zai-org/GLM-OCR" \
    --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": "zai-org/GLM-OCR",
		"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 "zai-org/GLM-OCR" \
        --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": "zai-org/GLM-OCR",
		"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 zai-org/GLM-OCR with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-OCR
```

GLM-OCR very slow on Tesla T4 (~40s per image) even with GPU — is this expected?

#13

by 905saini - opened Feb 6

Discussion

905saini

Feb 6

Hi,

I’m testing GLM-OCR on Google Colab with a Tesla T4 (15GB VRAM).

Setup:

Model: zai-org/GLM-OCR
Image size : 1024X1024
max_new_tokens :2048
GPU utilization ~60%, VRAM ~4.4GB

However, inference time is still ~40 seconds per image:

Questions:

Is ~40–50s on T4 expected for GLM-OCR?
Any recommended settings for faster inference ?

iyuge2

Z.ai org Feb 25

@905saini Hi, thanks for sharing the detailed setup and metrics — that’s very helpful.

We haven’t test GLM-OCR on a T4 GPU yet, so we don’t have an official reference for the expected latency in this configuration.

Could you let us know which inference framework you’re currently using?
For example: Transformers, vLLM, SGLang, or Ollama?

iyuge2

Z.ai org Feb 25

If possible, you can also share the image that you’re testing with. We can run it on our side to better understand the latency and give more specific feedback.

Bakanayatsu

Mar 1

Hi,

I’m testing GLM-OCR on Google Colab with a Tesla T4 (15GB VRAM).

Setup:

Model: zai-org/GLM-OCR
Image size : 1024X1024
max_new_tokens :2048
GPU utilization ~60%, VRAM ~4.4GB

However, inference time is still ~40 seconds per image:

Questions:

Is ~40–50s on T4 expected for GLM-OCR?

Any recommended settings for faster inference ?

T4 doesn't support bf16, are you using fp16?

905saini

Apr 2

•

edited Apr 3

@iyuge2 , @Bakanayatsu
Hi,
I have used Transformers setup and my data is normal tabular data.
like below attached image.

Also i have used bf16.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment