CoolFace
Modelpublic

cyberCyber99/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
2likes652downloads
Model Card

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive OptiQ 4bit

Source: ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16 Original: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Quantization

FieldValue
MethodOptiQ mixed-precision MLX
Target BPW4
Achieved BPW4.07
Candidate bits4, 8
Group size64
Calibrationoptiq (24 samples)
Model size18.17 GiB
Layer allocation14 high-bit / 377 low-bit
Layer policy entries391

Notes

  • —This is a text-only MLX export; vision components are omitted.
  • —Native MTP is disabled for this build.
  • —The original model is multimodal; this repository contains only the language model weights.
  • —Built from the bf16 source snapshot listed above.

Usage

bash
huggingface-cli download dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX --local-dir Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX
python -m mlx_lm.generate --model Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX --prompt "Write a short greeting."