Instructions to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 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 dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
# Run inference directly in the terminal:
llama cli -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
# Run inference directly in the terminal:
llama cli -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
# Run inference directly in the terminal:
./llama-cli -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Use Docker

docker model run hf.co/dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

LM Studio
Jan

vLLM

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dougvk/chandra-ocr-2-BF16-GGUF-RDNA4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dougvk/chandra-ocr-2-BF16-GGUF-RDNA4",
		"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/dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Ollama
How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Ollama:
```
ollama run hf.co/dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
```

Unsloth Studio

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 to start chatting

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

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 dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

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 "dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16" \
  --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"

Docker Model Runner
How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Docker Model Runner:
```
docker model run hf.co/dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16
```

Lemonade

How to use dougvk/chandra-ocr-2-BF16-GGUF-RDNA4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dougvk/chandra-ocr-2-BF16-GGUF-RDNA4:BF16

Run and chat with the model

lemonade run user.chandra-ocr-2-BF16-GGUF-RDNA4-BF16

List all available models

lemonade list

Chandra OCR 2 BF16 GGUF — one-GPU RDNA 4 validation

Unofficial, reproducible BF16 GGUF conversion of datalab-to/chandra-ocr-2, validated end to end with llama.cpp on one AMD Radeon RX 9070 XT (gfx1201).

This is a container conversion, not a fine-tune, new model, or claim of improved OCR quality. The main GGUF preserves BF16 precision while omitting Chandra's unused multi-token-prediction (MTP) draft head. The vision projector is BF16. The original model, architecture, training, and authorship belong to Datalab.

Files

File	Bytes	SHA-256
`chandra-ocr-2.BF16.gguf`	9,695,791,648	`4e9d5fa9854cf820d4425d28034df31ec1221a7f9d1082b0c4359d79f318cb56`
`chandra-ocr-2.mmproj-bf16.gguf`	675,568,864	`54ddb8285933512cdbf1c84238aa0435b473a6efef2caeda8ca802c2899e87b3`
`chat_template.jinja`	7,622	`0d158f349ca965f7eea9db0eb45cd177b85bb0e4ae05dcdd0f060da8f7d41812`

The complete machine-readable provenance is in manifest.json.

Pinned provenance

Source model: datalab-to/chandra-ocr-2
Source revision: af93b47dba1b47b6640c86ccf487ed2260ab9a09
Source model.safetensors SHA-256: 0804568be9f099d6479fad9ed77a4da4611f3c1e7bc6e009af7dce45e8aa3847
Converter/runtime: ggml-org/llama.cpp
Converter revision: 8f5ab832ca7d8a7b4f23687693fb8b0ecbc227e7
chandra-ocr: 0.2.0

See CONVERSION.md for the exact commands and integrity checks.

Verified configuration

Component	Verified value
GPU	AMD Radeon RX 9070 XT, 16 GB (`gfx1201`)
GPU allocation	One isolated GPU; full layer offload
OS / kernel	Ubuntu 24.04.4 / 6.17.0-40-generic
ROCm	7.2.1
llama.cpp	`8f5ab832ca7d8a7b4f23687693fb8b0ecbc227e7`
Context	24,576 tokens
Maximum tested output envelope	12,384 tokens
Observed model-process VRAM peak	Approximately 11.2 GB

The GGUF format is not RDNA4-specific. gfx1201 is the hardware on which this exact pair completed image, PDF, financial-table, handwritten-document, deterministic-output, and lifecycle tests. Other llama.cpp-supported hardware may work but is not validated here.

Run with llama.cpp and the Chandra CLI

Build llama.cpp for your accelerator, then start a loopback server. These are the validated inference settings; replace the device selector as appropriate for your machine.

ROCR_VISIBLE_DEVICES=GPU-YOUR-STABLE-UUID HIP_VISIBLE_DEVICES=0 \
llama-server \
  --model chandra-ocr-2.BF16.gguf \
  --mmproj chandra-ocr-2.mmproj-bf16.gguf \
  --alias chandra \
  --host 127.0.0.1 \
  --port 18100 \
  --ctx-size 24576 \
  --n-gpu-layers 999 \
  --split-mode none \
  --main-gpu 0 \
  --flash-attn on \
  --fit off \
  --parallel 1 \
  --batch-size 2048 \
  --ubatch-size 512 \
  --jinja \
  --chat-template-file chat_template.jinja \
  --image-min-tokens 1024

In another shell:

python3 -m venv .venv
.venv/bin/pip install 'chandra-ocr==0.2.0'

VLLM_API_BASE=http://127.0.0.1:18100/v1 \
VLLM_API_KEY=EMPTY \
VLLM_MODEL_NAME=chandra \
.venv/bin/python -m chandra.scripts.cli input.pdf output \
  --method vllm \
  --batch-size 1 \
  --max-workers 1 \
  --max-retries 2 \
  --max-output-tokens 12384 \
  --no-images \
  --no-html

Do not expose an unauthenticated llama.cpp server to a public network. Generative OCR can omit or hallucinate content; verify consequential documents against their source.

Validation result and limits

The exact-pinned conversion matched the public comparison BF16 tensor schema. All projector tensor payloads matched. In the main file, every tensor payload matched except twelve scalar F32 values across ten ssm_a tensors; the maximum absolute difference was 9.5367431640625e-07. Accepted OCR outputs matched. There is no evidence that this conversion improves OCR quality over other correct BF16 conversions.

The useful contribution is the pinned, MTP-free artifact pair; complete provenance; one-16-GB-GPU validation; and a reproducible launch envelope.

License and attribution

Chandra OCR 2 weights use Datalab's AI Pubs Open RAIL-M License (Modified). It contains usage, redistribution, commercial, competitive-use, attribution, and share-alike conditions. Read LICENSE in full before using or redistributing these files. The license and its restrictions apply to this derivative conversion.

Modified-file notice: the original Chandra OCR 2 checkpoint was converted to GGUF at the pinned llama.cpp revision; the unused MTP draft head was omitted from the main GGUF; model tensor precision otherwise remains BF16. No Datalab endorsement is claimed.

Downloads last month: 280

GGUF

Model size

5B params

Architecture

qwen35

Hardware compatibility

16-bit

Model tree for dougvk/chandra-ocr-2-BF16-GGUF-RDNA4

Base model

datalab-to/chandra-ocr-2

Quantized

(35)

this model