Instructions to use 1qh/chandra-ocr-2-oq4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 1qh/chandra-ocr-2-oq4-mlx 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("1qh/chandra-ocr-2-oq4-mlx")
config = load_config("1qh/chandra-ocr-2-oq4-mlx")

# 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 Settings
LM Studio

How to use 1qh/chandra-ocr-2-oq4-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "1qh/chandra-ocr-2-oq4-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "1qh/chandra-ocr-2-oq4-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 1qh/chandra-ocr-2-oq4-mlx with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "1qh/chandra-ocr-2-oq4-mlx"

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 1qh/chandra-ocr-2-oq4-mlx

Run Hermes

hermes

OpenClaw new

How to use 1qh/chandra-ocr-2-oq4-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "1qh/chandra-ocr-2-oq4-mlx"

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 "1qh/chandra-ocr-2-oq4-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

1qh/chandra-ocr-2-oq4-mlx

datalab-to/chandra-ocr-2 quantized with oQ (oMLX v0.5.3) at level 4.0, data-driven mixed precision: oQ measures each layer's quantization error through calibration and allocates bits where the measurement says they matter, rather than by a fixed per-tensor rule.


Base	`datalab-to/chandra-ocr-2`
oQ level	`4.0` (effective ~4.6–4.7 bits/weight)
Size	3.2 GB (from 9.1 GB bf16)
Sensitivity entries	248
oMLX	v0.5.3

Table-column fidelity: FAILS. On the OCR fidelity check this build shifts config-table values by one column (every label carries the next column's value) while emitting well-formed output. Prefer level 5 or higher when table structure matters.

Vision weights are kept fp16; only the language tower is quantized.

Use

from mlx_vlm import load, generate
model, processor = load("1qh/chandra-ocr-2-oq4-mlx")

Downloads last month: 27

Safetensors

Model size

1B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for 1qh/chandra-ocr-2-oq4-mlx

Base model

datalab-to/chandra-ocr-2

Quantized

(35)

this model