Modelpublic

dfp-official/Qwen3.8-Flash-Next-oQ8e-mtp

sourceHugging Faceupdated 1mo agoView on Hugging Face

1likes588downloads

Model Card

Qwen3.8-Flash-Next-oQ8e-mtp

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

Quantization details

—Model type: qwen4_exp
—Bits: 8
—Group size: 64
—Format: MLX safetensors