Modelpublic

brainworkup/NuMarkdown-8B-Thinking-oQ8

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes9downloads

Model Card

[!IMPORTANT] This quantization was uploaded on 2026-07-01 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

NuMarkdown-8B-Thinking-oQ8

This model was quantized using oQ (oMLX v0.4.5.dev1) mixed-precision quantization.

Quantization details

—Model type: qwen25vl
—Bits: 8
—Group size: 64
—Format: MLX safetensors