Back to @hjbhjh's timeline
hjbhjh shared this post · 1h ago
X
Sudo su
Sudo su

i went through every uncensored and abliterated models on hugging face and picked the best ones for each vram tier from 8 to 24gb.

welcome to the danger zone ⚠️

━━━━━━━━━━━━━━━━━━━━

8gb · rtx 3060 ti, 3070, 4060, 5060, 4060 ti 8gb, 5060 ti 8gb · amd rx 6600, 6650 xt, 7600, 9060 xt 8gb · the base runs 42.8 tok/s on a 3060 ti 8gb out to a 96k window

  1. bonsai 2 27b heretic, 1-bit, 5.95gb, refusals 95 to 0 out of 100, 147k downloads this month

http://huggingface.co/OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF

  1. bonsai 2 27b abliterated, refusals 83% to 0%, mmlu holds at 78%, 77k downloads

http://huggingface.co/BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF

  1. bonsai 2 27b crack, harmbench refusals 93% to 0% → http://huggingface.co/dealignai/Bonsai-2-27B-1bit-CRACK-GGUF

older 8gb cards · gtx 1070, 1080 · the base runs 42 tok/s on a 2016 gtx 1080

  1. gemma 4 e4b aggressive, 5.3gb, 0 refusals out of 465, 1.43m downloads this month

http://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

  1. gemma 4 e4b heretic, refusals 99 to 3 out of 100

http://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF

━━━━━━━━━━━━━━━━━━━━

12gb · rtx 3060 12gb, 3080 12gb, 4070, 4070 super, 4070 ti, 5070 · amd rx 6700 xt, 6750 xt, 7700 xt · base bonsai 2 runs 50.1 tok/s on a 3060 12gb with my kernel and the speed head

  1. bonsai 2 27b abliterated v2 with the mtp speed head, 7.7gb, refusals 84% to 0%

http://huggingface.co/BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF

  1. qwen 3.8 27b abliterated squeezed to 10gb with gsq-rco, 2.12m downloads this month

http://huggingface.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

  1. qwen 3.8 27b heretic gsq-rco, 9.3 to 10.1gb, refusals 0 to 1 out of 100

http://huggingface.co/0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF

  1. gemma 4 12b heretic, 7.4gb, 120k downloads

http://huggingface.co/culturerevolt/gemma-4-12b-heretic-abliterated-GGUF

━━━━━━━━━━━━━━━━━━━━

16gb · rtx 4060 ti 16gb, 5060 ti 16gb, 4070 ti super, 4080, 5070 ti, 5080 · amd rx 6800, 6900 xt, 7600 xt, 7800 xt, 9060 xt 16gb, 9070 xt · base bonsai 2 runs 67.3 tok/s on a 5060 ti 16gb with everything on

  1. qwen 3.8 27b heretic ara, built for 16gb, 14gb

http://huggingface.co/Bucoid/Qwen3.8-27B-Heretic-Ara-16GB-VRAM-IQ4-XS-MTP-GGUF

  1. qwen 3.8 27b aggressive with the mtp head, 12.8 to 15.7gb, 0 refusals out of 465, 2.06m downloads this month

http://huggingface.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

  1. bonsai 2 27b heretic with the full 262k window, the speed head and vision all on

http://huggingface.co/OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF

  1. gemma 4 26b a4b abliterated, moe with 4b active per token, 13.4gb

http://huggingface.co/groxaxo/Huihui-gemma-4-26B-A4B-it-abliterated-GGUF

━━━━━━━━━━━━━━━━━━━━

24gb, the danger zone · rtx 3090, 3090 ti, 4090 ·

amd rx 7900 xtx, and the 20gb 7900 xt fits these too ·

base qwen 3.8 27b q4 runs 41.3 tok/s on my 3090 with the mtp head, owners report 61 on a 3090 ti and 76 on a 4090

  1. qwen 3.8 27b uncensored, q4 16.8gb, 2.31m downloads this month

http://huggingface.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF

  1. qwen 3.8 27b abliterated, q4 16.8gb, 2.12m downloads

http://huggingface.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

  1. qwen 3.8 27b aggressive with the mtp head, 0 refusals out of 465, 2.06m downloads

http://huggingface.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

  1. qwen 3.8 27b heretic, refusals 0 to 1 out of 100

http://huggingface.co/0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

  1. qwen 3.8 27b fable cold fusion, the uncensored coder merge, 2.09m downloads

http://huggingface.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

  1. qwen 3.6 35b a3b aggressive, moe with 3b active, 11.9m downloads all time and the most liked on this list

http://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

━━━━━━━━━━━━━━━━━━━━

refusal numbers are each releaser's own test, so read them per model, and the speeds are the base models on nvidia cards, these builds keep the same size so they run the same. amd cards run the same files on llama.cpp's vulkan or rocm backends, the bonsai builds run on prismml's llama.cpp

no refusals means no guardrails, you own what you ask. bookmark this, find your card and pull one tonight

2.2K 32 226 155.8K