Instructions to use prithivMLmods/chandra-ocr-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/chandra-ocr-2-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/chandra-ocr-2-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/chandra-ocr-2-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/chandra-ocr-2-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/chandra-ocr-2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/chandra-ocr-2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/chandra-ocr-2-GGUF",
		"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/prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/chandra-ocr-2-GGUF 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 "prithivMLmods/chandra-ocr-2-GGUF" \
    --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": "prithivMLmods/chandra-ocr-2-GGUF",
		"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 "prithivMLmods/chandra-ocr-2-GGUF" \
        --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": "prithivMLmods/chandra-ocr-2-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/chandra-ocr-2-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/chandra-ocr-2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/chandra-ocr-2-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/chandra-ocr-2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.chandra-ocr-2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/chandra-ocr-2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/chandra-ocr-2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "prithivMLmods/chandra-ocr-2-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

chandra-ocr-2-GGUF

Chandra-OCR-2 from Datalab is a state-of-the-art OCR model that outputs structured markdown, HTML, or JSON while preserving precise layout information from images and PDFs across 90+ languages. It achieves SOTA benchmarks with 85.9% on olmocr and 77.8% multilingual score (+12% over Chandra 1), delivering major gains in math equation parsing, complex table reconstruction (including merged cells), handwriting recognition, form elements like checkboxes, and wide-document layouts alongside vastly improved image captioning and diagram extraction. Available via free playground, hosted API for production speed/accuracy, or local deployment through HuggingFace Transformers/vLLM, it excels at transforming challenging real-world documents—financial filings, research papers, historical scans, multilingual forms—into semantically rich structured data for downstream AI pipelines and automation workflows.

MTP — Speculative Decoding: No

Model Files

File Name	Quant Type	File Size	File Link	Description
chandra-ocr-2.BF16.gguf	BF16	9.7 GB	Link	Full BF16 weights. Highest quality, largest file size.
chandra-ocr-2.F16.gguf	F16	9.7 GB	Link	Full F16 weights. Highest quality, largest file size.
chandra-ocr-2.Q2_K.gguf	Q2_K	2.12 GB	Link	Lowest quality, smallest size, good for extreme low RAM availability.
chandra-ocr-2.Q3_K_L.gguf	Q3_K_L	2.69 GB	Link	Lower quality but usable, good for low RAM availability.
chandra-ocr-2.Q3_K_M.gguf	Q3_K_M	2.54 GB	Link	Low quality.
chandra-ocr-2.Q3_K_S.gguf	Q3_K_S	2.34 GB	Link	Lowest of the Q3 variants, very low RAM usage.
chandra-ocr-2.Q4_0.gguf	Q4_0	2.9 GB	Link	Standard 4-bit quantization, older format but widely supported.
chandra-ocr-2.Q4_K_M.gguf	Q4_K_M	3.07 GB	Link	Good quality, default size for most use cases, recommended.
chandra-ocr-2.Q4_K_S.gguf	Q4_K_S	2.92 GB	Link	Slightly lower quality with more space savings, recommended.
chandra-ocr-2.Q5_0.gguf	Q5_0	3.43 GB	Link	Standard 5-bit quantization, older format but widely supported.
chandra-ocr-2.Q5_K_M.gguf	Q5_K_M	3.51 GB	Link	High quality, recommended.
chandra-ocr-2.Q5_K_S.gguf	Q5_K_S	3.43 GB	Link	High quality, recommended.
chandra-ocr-2.Q6_K.gguf	Q6_K	3.99 GB	Link	Very high quality, near perfect, recommended.
chandra-ocr-2.Q8_0.gguf	Q8_0	5.16 GB	Link	Extremely high quality, generally unneeded but max available quant.
chandra-ocr-2.mmproj-bf16.gguf	mmproj-bf16	676 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.
chandra-ocr-2.mmproj-f16.gguf	mmproj-f16	676 MB	Link	Multimodal projection file in F16 format. Used for vision/language models.
chandra-ocr-2.mmproj-q8_0.gguf	mmproj-q8_0	367 MB	Link	Multimodal projection file in Q8_0 quantization. Smaller size for vision capabilities.

Run Inference

# Download the image
wget -O /path/to/models/input.jpeg \
  "/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F65bb837dbfb878f46c77de4c%2FEF8cldKHhUEO3MZPZSD19.jpeg"

# Run Chandra OCR 2 "Q5_K_M" with vision support
/data/llama.cpp/build/bin/llama-cli \
  -m /path/to/models/chandra-ocr-2.Q5_K_M.gguf \
  --mmproj /path/to/models/chandra-ocr-2.mmproj-bf16.gguf  \
  -ngl 99 \
  -c 16384 \
  --cache-type-k q8_0 \
  --seed 42 \
  -n 8192 \
  -st \
  --image /path/to/models/input.jpeg \
  -p "OCR the image"