Modelpublic

root4k/Huihui-Qwen3.8-27B-abliterated-oQ4e-mtp

sourceHugging Faceupdated 1mo agoView on Hugging Face

9likes3.3kdownloads

Model Card

[!IMPORTANT] This quantization was uploaded on 2026-08-24 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Huihui-Qwen3.8-27B-abliterated-oQ4e-mtp

This model was quantized using oQ (oMLX v0.6.3rc2) mixed-precision quantization.

Quantization details

—Model type: qwen3_5
—Bits: 4
—Group size: 64
—Format: MLX safetensors