Modelpublic

funnygeeker/Qwen3.8-35B-A3B-Distill-oQ6e-fp16-mtp

sourceHugging Faceapache-2.0updated 2d agoView on Hugging Face

1likes641downloads

Model Card

[!IMPORTANT] This quantization was uploaded on 2026-09-20 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.8-35B-A3B-Distill-oQ6e-fp16-mtp

This model was quantized using oQ (oMLX v0.7.0.dev4) mixed-precision quantization.

Quantization details

—Model type: qwen35moe
—Bits: 6
—Group size: 64
—Format: MLX safetensors