license: apache-2.0 base_model: ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16 library_name: mlx tags:

• mlx
• omlx
• qwen3.6
• qwen3.5-moe
• text-generation
• oq8

Qwen3.6-35B-A3B Uncensored HauhauCS Aggressive text oQ8

This is an oMLX oQ8 text-only quantization of ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16.

Quantization

• Quantizer: oMLX oQ
• Level: oQ8
• Group size: 64
• Non-quantized/scales dtype: bfloat16
• Output size: about 34 GB
• Vision weights: omitted
• Native MTP: disabled

Notes

The source checkpoint is a VLM-style BF16 conversion. This repository contains the text model only, with the language weights remapped into the Qwen3_5MoeForCausalLM layout. Native MTP was also disabled because the BF16 source did not include mtp.* tensors.

The quantized model was smoke-tested with mlx_lm.load(..., lazy=True).