Hugging Face's logo

matthewdubois
/
GLM-OCR-3bit-mlx

Image-Text-to-Text
MLX
Safetensors
glm_ocr
3-bit
quantized
conversational
Model card Files
xet
 Community
How to use from
Pi
Start the MLX server 
# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "matthewdubois/GLM-OCR-3bit-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": "matthewdubois/GLM-OCR-3bit-mlx"
        }
      ]
    }
  }
}
Run Pi 
# Start Pi in your project directory:
pi
Quick Links

GLM-OCR 3-bit MLX

3-bit quantized MLX conversion of zai-org/GLM-OCR for on-device inference on Apple Silicon.

  • Base model: zai-org/GLM-OCR (MIT license)
  • Quantization: 3-bit via mlx-vlm
  • Size: ~1.1 GB
  • Use case: Business card OCR / document text extraction

Converted using mlx_vlm.convert --q-bits 3.

Downloads last month
31
Safetensors
Model size
0.2B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

3-bit

Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for matthewdubois/GLM-OCR-3bit-mlx

Base model

zai-org/GLM-OCR
Quantized
(26)
this model