huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-v3

Text Generation • 0.5B • Updated Apr 28, 2025 • 1.62k • • 4

Note abliterated A1 dense safetensors, width 896, 1.0 GB

DavidAU/gemma-3-1b-it-heretic-extreme-uncensored-abliterated

Text Generation • 1.0B • Updated Nov 21, 2025 • 1.64k • • 62

Note heretic A2 dense safetensors, width 1152, 2.0 GB

huihui-ai/Huihui-Qwen3.5-2B-abliterated

Image-Text-to-Text • 2B • Updated Mar 3 • 1.69k • 52

Note abliterated A3 dense safetensors, width 2048, 4.6 GB

huihui-ai/Huihui-Qwen3-4B-abliterated-v2

Text Generation • 4B • Updated Jun 19, 2025 • 2.39k • • 66

Note abliterated A4 dense safetensors, width 2560, 8.0 GB; pair with Qwen/Qwen3-4B

Qwen/Qwen3-4B

Text Generation • 4B • Updated Jul 26, 2025 • 8.42M • • 783

Note clean A5 dense safetensors, width 2560, 8.0 GB; clean pair of A4

huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2

Text Generation • 8B • Updated Apr 28, 2025 • 6.18k • • 74

Note abliterated A6 dense safetensors, width 3584, 15.2 GB

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated

Text Generation • 8B • Updated Sep 14, 2024 • 6.48k • • 221

Note abliterated A7 dense safetensors, width 4096, 16.1 GB; holdout

huihui-ai/Qwen3-14B-abliterated

Text Generation • 15B • Updated Jun 17, 2025 • 147 • • 54

Note abliterated A8 dense safetensors, width 5120, 29.5 GB (gated: auto); same model as B12

ArRENCEAI/DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED

2B • Updated Aug 11 • 1.15k • 5

Note obliterated quant: Q6_K B9 dense GGUF, width 1536, 1.5 GB

saidutta69/SmolLM3-3B-heretic

Text Generation • 3B • Updated 3 days ago • 1.73k

Note heretic quant: Q8_0 B10 dense GGUF, width 2048, 3.3 GB

bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF

Text Generation • 8B • Updated Nov 14, 2024 • 57.5k • 97

Note abliterated quant: Q8_0 B11 dense GGUF, width 3584, 8.1 GB

bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF

Text Generation • 15B • Updated May 6, 2025 • 45.6k • 25

Note abliterated quant: Q8_0 B12 dense GGUF, width 5120, 15.7 GB; same model as A8 (format effect)

huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

Image-Text-to-Text • 27B • Updated 25 days ago • 3.39M • 1.73k

Note abliterated quant: Q8_0 B13 dense GGUF, width 5120, 65 layers, 29.0 GB

mradermacher/Qwen3-32B-abliterated-GGUF

33B • Updated 13 days ago • 5.1k • 5

Note abliterated quant: Q8_0 B14 dense GGUF, width 5120, 64 layers, 34.8 GB; holdout

bartowski/Llama-3.3-70B-Instruct-abliterated-GGUF

Text Generation • 71B • Updated Dec 24, 2024 • 61.7k • 39

Note abliterated quant: Q3_K_M B15 dense GGUF, width 8192, 80 layers, 34.3 GB; holdout

unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Image-Text-to-Text • 36B • Updated May 20 • 1.68M • 1.03k

Note clean quant: Q8_0 C16 MoE with shared expert, width 2048, 37.8 GB; clean pair of C17

mradermacher/Huihui-Qwen3.6-35B-A3B-abliterated-GGUF

35B • Updated 25 days ago • 91.3k • 15

Note abliterated quant: Q8_0 C17 MoE with shared expert, width 2048, 36.9 GB

unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF

31B • Updated Jul 31, 2025 • 527k • 327

Note clean quant: Q8_0 C18 MoE without shared expert, 32.5 GB; clean pair of C19

mradermacher/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-GGUF

31B • Updated Aug 3, 2025 • 59.3k • 39

Note abliterated quant: Q8_0 C19 MoE without shared expert, 32.5 GB; holdout

unsloth/gpt-oss-20b-GGUF

Text Generation • 21B • Updated Dec 19, 2025 • 586k • 899

Note clean quant: Q8_0 C20 MoE gpt-oss, 12.1 GB; MXFP4 experts not decodable (exit 2 expected)

bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF

Text Generation • 21B • Updated Aug 8, 2025 • 10k • 43

Note abliterated quant: Q8_0 C21 MoE gpt-oss, 22.3 GB; abliterated pair of C20

ibm-granite/granite-4.0-h-tiny-GGUF

7B • Updated Apr 23 • 9.76k • 29

Note clean quant: Q8_0 C22 hybrid Mamba MoE, 7.4 GB; clean pair of C23

mradermacher/Huihui-granite-4.0-h-tiny-abliterated-GGUF

7B • Updated Oct 4, 2025 • 536 • 2

Note abliterated quant: Q8_0 C23 hybrid Mamba MoE, 7.4 GB