Modelpublic

dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-text-oQ4

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

5likes611downloads

Model Card

Qwen3.6-35B-A3B Uncensored HauhauCS Aggressive text oQ4

This is an oMLX oQ4 text-only quantization of ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16.

Quantization

—Quantizer: oMLX oQ
—Level: oQ4
—Group size: 64
—Non-quantized/scales dtype: bfloat16
—Output size: about 19 GB
—Vision weights: omitted
—Native MTP: disabled

Notes

The source checkpoint is a VLM-style BF16 conversion. oMLX's full VLM sensitivity path did not support this checkpoint during local quantization, so this repository contains the text model only. Native MTP was also disabled because the BF16 source did not include mtp.* tensors.

The quantized model was smoke-tested through a local oMLX OpenAI-compatible /v1/chat/completions request.