dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

Image-Text-to-Text • 34B • Updated 5 days ago • 1.71k • 4

Note HarmBench: 308/320 (96.2%) JANG_1L CRACK -- 112 GB -- MMLU: 88.9% VS JANG_1L Base -- 112 GB -- MMLU: 87.0% VS MLX 3bit -- incoherent and broken lol VS MLX 4-bit -- 209 GB -- MMLU: 94.0%

dealignai/Qwen3.5-VL-122B-A10B-UNCENSORED-JANG_2S

Image-Text-to-Text • 11B • Updated 5 days ago • 1.36k • 1

Note HarmBench: 91.2% (292/320) JANG_2S + CRACK -- This model -- 35 GB -- MMLU: 77.5% VS JANG_2S -- (base, no CRACK) -- 38 GB -- - MMLU: 79% VS MLX 4-bit -- (base, no CRACK) -- 64 GB -- MMLU: 85% VS MLX 2-bit - (base, no CRACK) -- 36 GB -- - MMLU: 56.5%

dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK

Image-Text-to-Text • 5B • Updated 5 days ago • 1.25k • 4

Note HarmBench: 98.4% (315/320) JANG_4K CRACK -- This model -- 18 GB -- MMLU: 69.2% -- 110 tok/s vs JANG_4K (base) -- Unmodified JANG -- 18 GB -- MMLU: 70.8% -- 110 tok/s VS JANG_2S (base) -- Lower precision -- 11 GB -- MMLU: ~65% -- ~120 tok/s VS MLX 4-bit -- Uniform quant -- 20 GB -- MMLU: ~60% -- ~85 tok/s

dealignai/Qwen3.5-VL-27B-JANG_4S-CRACK

Image-Text-to-Text • 5B • Updated 5 days ago • 1.07k • 3

Note HarmBench: 75.0% (240/320) JANG_4S CRACK -- This model -- 16 GB -- 27 tok/s -- MMLU: 83.1% VS JANG_4S (base) -- Unmodified JANG -- 16 GB -- 35 tok/s -- MMLU: 84.5% VS MLX 4-bit -- Uniform quant -- 14 GB -- 20 tok/s -- MMLU: 84.5% VS MLX 8-bit -- 2x larger -- 29 GB -- ~15 tok/s -- MMLU: ~86%

dealignai/Qwen3.5-VL-4B-JANG_4S-CRACK

Image-Text-to-Text • 1B • Updated 5 days ago • 2.96k • 6

Note HarmBench: 91.2% (292/320) JANG_4S CRACK -- This model -- 3 GB -- 134 tok/s -- MMLU: 63.1% VS JANG_4S (base) -- Unmodified JANG -- 3 GB -- 134 tok/s -- MMLU: 67.5% VS MLX 4-bit -- Uniform quant -- -- 2.2 GB -- ~100 tok/s -- MMLU: 67.0%

dealignai/Qwen3.5-VL-9B-JANG_4S-CRACK

Image-Text-to-Text • 2B • Updated 5 days ago • 1.95k • 5

Note HarmBench: 72.5% (232/320) JANG_4S CRACK -- This model -- 6 GB -- MMLU: 70.8% VS JANG_4S (base) -- Unmodified JANG -- 6 GB -- MMLU: 73.0% VS MLX 4-bit -- Uniform quant -- 4.7 GB -- MMLU: 72.5%

dealignai/Qwen3.5-VL-122B-A10B-JANG_4K-CRACK

Image-Text-to-Text • 18B • Updated 5 days ago • 1.16k • 3

Note HarmBench: 78.4% (251/320) JANG_4K CRACK -- 62 GB -- MMLU: 81.5% vs JANG_4K Base -- 69 GB -- MMLU: 86% vs JANG_2S CRACK -- 35 GB -- MMLU: 77.5% vs MLX 2-bit -- 36 GB -- MMLU: 56.5% vs MLX 4-bit -- 64 GB -- MMLU: 85%

dealignai/Mistral-Small-4-119B-JANG_4M-CRACK

Image-Text-to-Text • 19B • Updated 5 days ago • 803 • 4

Note HarmBench: 95.3% (305/320) JANG_4M CRACK -- 64 GB -- MMLU: 90.9% (189/208) VS JANG_2L CRACK -- 37 GB -- MMLU: 89.9% (187/208)

dealignai/Mistral-Small-4-119B-JANG_2L-CRACK

Image-Text-to-Text • 12B • Updated 5 days ago • 801 • 2

Note HarmBench: 95.9% (307/320) JANG_2L CRACK -- 37 GB -- MMLU: 89.9% (187/208) VS ANG_4M CRACK -- 64 GB -- MMLU: 90.9% (189/208)