Instructions to use mlx-community/DeepSeek-OCR-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/DeepSeek-OCR-8bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/DeepSeek-OCR-8bit", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("mlx-community/DeepSeek-OCR-8bit", trust_remote_code=True, dtype="auto")

MLX

How to use mlx-community/DeepSeek-OCR-8bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/DeepSeek-OCR-8bit")
config = load_config("mlx-community/DeepSeek-OCR-8bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/DeepSeek-OCR-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/DeepSeek-OCR-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/DeepSeek-OCR-8bit",
		"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/mlx-community/DeepSeek-OCR-8bit

SGLang

How to use mlx-community/DeepSeek-OCR-8bit 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 "mlx-community/DeepSeek-OCR-8bit" \
    --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": "mlx-community/DeepSeek-OCR-8bit",
		"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 "mlx-community/DeepSeek-OCR-8bit" \
        --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": "mlx-community/DeepSeek-OCR-8bit",
		"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 mlx-community/DeepSeek-OCR-8bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/DeepSeek-OCR-8bit
```

ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.

by sjwwork - opened Jan 8

Discussion

sjwwork

Jan 8

run in the LM Studio 0.3.37 (Build 1)：

2026-01-08 17:15:33 [DEBUG]
ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.

At:
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_vlm/models/deepseekocr/deepseekocr.py(304): get_input_embeddings
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_vlm/models/deepseekocr/deepseekocr.py(326): call
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_engine/vision_model_kit/vision_model_wrapper.py(92): call
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_lm/generate.py(381): _model_call
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_lm/generate.py(391): _step
/Users/sjw/.lmstudio/extensions/backends/vendor/_amphibian/app-mlx-generate-mac14-arm64@7/lib/python3.11/site-packages/mlx_lm/generate.py(444): generate_step
2026-01-08 17:15:33 [DEBUG]
[lmstudio-llama-cpp] Error in predictTokens: Error in iterating prediction stream: ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.
2026-01-08 17:15:33 [DEBUG]
1 Error predicting: _0x3844b4 [Error]: Error in iterating prediction stream: ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.
at _0x144d91..predictTokens (/Applications/LM Studio.app/Contents/Resources/app/.webpack/lib/llmworker.js:85:29884)
at async _0x196be6.predictTokens (/Applications/LM Studio.app/Contents/Resources/app/.webpack/lib/llmworker.js:124:17625)
at async _0x196be6.handleMessage (/Applications/LM Studio.app/Contents/Resources/app/.webpack/lib/llmworker.js:124:7045) {
cause: undefined,
suggestion: undefined,
errorData: undefined,
data: undefined,
displayData: undefined,
title: 'Error in iterating prediction stream: ValueError: [broadcast_shapes] Shapes (1183,1280) and (1182,1280) cannot be broadcast.'
}
2026-01-08 17:15:33 [ERROR]
[deepseek-ocr] Error: Channel Error

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