You can deploy this model and start earning money today!

jrcrittenden/
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit

Name: Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit
Availability: InStock

Views

No views yet

Fable-Fusion-711 — MLX 5-bit (vision retained)

5-bit / group-size 64 affine MLX quant of DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP, converted directly from the bf16 safetensors (no GGUF round-trip).

Vision tower kept at bf16 (--skip-vision) — image input works.
MTP head stripped (unused by mlx-lm / vllm-mlx serving).
Both source chat templates included (chat_template.jinja, chat_template-instruct.jinja).

Serve, e.g.: vllm-mlx serve jrcrittenden/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit --reasoning-parser qwen3

Total size: 19.4 GB.