divinetribe/Llama-3.3-70B-Instruct-abliterated-8bit-mlx

Text Generation • 20B • Updated 7 days ago • 1.32k • 3

Note llama 3.3 70b, 8-bit. ~75 gb, the heaviest.

divinetribe/Qwen3.6-27B-abliterated-4bit-mlx

Text Generation • 4B • Updated 7 days ago • 191

Note qwen3.6 27b, 4-bit. ~15 gb.

divinetribe/Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated-4bit-mlx

80B • Updated Jun 23 • 21 • 1

Note coding, reasoning-distilled, 4-bit. ~45 gb.

divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Text Generation • 2B • Updated 7 days ago • 724 • 1

Note hermes 4 14b, 4-bit. ~8 gb.

divinetribe/Huihui-Qwen3-8B-abliterated-v2-4bit-mlx

Text Generation • 1B • Updated 7 days ago • 68

Note the lightest, 4-bit. ~5 gb, easiest place to start.

divinetribe/gemma-4-31b-it-abliterated-4bit-mlx

Text Generation • 5B • Updated 7 days ago • 414 • 1

Note gemma 4 31b, 4-bit. text only. the one i run daily. ~17 gb.

divinetribe/Huihui-gemma-4-31B-it-abliterated-4bit-mlx

Text Generation • 5B • Updated 7 days ago • 192

Note gemma 4 31b, huihui abliteration, 4-bit. text only. ~17 gb.

divinetribe/gemma-4-12B-it-abliterated-4bit-mlx-text

Text Generation • 3B • Updated 7 days ago • 214

Note text-only build of the 12b for mlx-lm setups. ~11 gb.