Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp4-text-mlx
Text Generation • 27B • Updated • 1.14k
Qwen3.8 27B AEON Ultimate Uncensored MLX Quants
AEON Qwen3.8 27B MLX text/vision quants: MXFP4, MXFP8, native-MTP, and the benchmark-selected attention8 + BF16-recurrence hybrid.
Note Compact language-only MXFP4 MLX build.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp8-text-mlx
Text Generation • 27B • Updated • 846Note Higher-precision language-only MXFP8 MLX build.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp4-vision-mlx
Image-Text-to-Text • 27B • Updated • 937Note Vision-preserving MXFP4 MLX build.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp8-vision-mlx
Image-Text-to-Text • 27B • Updated • 820Note Vision-preserving MXFP8 MLX build.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp4-vision-mtplx
Image-Text-to-Text • 27B • Updated • 1.86k • 1Note MXFP4 vision body with the source model's native BF16 MTP sidecar.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-mxfp8-vision-mtplx
Image-Text-to-Text • 27B • Updated • 1.73k • 2Note MXFP8 vision body with the source model's native BF16 MTP sidecar.
Shiftedx/qwen3.8-27b-aeon-ultimate-uncensored-attention8-bf16recurrence-vision-mtplx
Image-Text-to-Text • 27B • Updated • 8.06k • 3Note Benchmark-selected attention8 + BF16-recurrence mixed-affine vision model with native BF16 MTP.