license: other
base_model:

• llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved
  tags:
• mlx
• omlx
• oq
• oq4
• qwen3.6
• mtp
• vision
• image-text-to-text
  pipeline_tag: image-text-to-text
  library_name: mlx

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-oQ4-MLX

This repository contains an oMLX oQ4 mixed-precision MLX quantization of
llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved with both the vision encoder and Native MTP tensors preserved.

This is a replacement build for the earlier Native-MTP-Preserved MLX artifact
that preserved MTP but omitted the vision-side tensors. The source VLM config is
kept functionally equivalent, with vision_config.model_type patched to
qwen3_5 for current MLX-VLM/oMLX compatibility.

Variant

• Quantization: oQ4
• Variant: Native MTP Preserved VLM
• Vision tensors: preserved
• MTP tensors: preserved
• Text-only: false
• Approximate target density: 4.89 bpw.

Usage

omlx serve dawncr0w/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-oQ4-MLX

For direct Python loading, use the VLM loader from the bundled oMLX/MLX-VLM runtime.

Validation

Local validation completed with the bundled oMLX runtime:

loader: mlx_vlm.load_model with oMLX VLM/MTP patches
load smoke test: passed
peak memory: 15.855 GB
visual tensors: 333
mtp tensors: 29

Source

• BF16 source checkpoint: llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved
• BF16 GGUF reference: llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF
• Quantization tool: oMLX oQ

Upstream model card license tag: apache-2.0.