Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic
from nightmedia/Qwen3.5-9B-DS9-USS-Defiant
Abliterated models that fit in 8 GB of GPU memory at the Q4_K_M quantisation with a 4,096-token context — RTX 3070, 4060 and comparable cards. 278 models qualify, the largest being 11B parameters at roughly 7.5 GB. Estimates are derived from parameter counts, not measured.
Need a figure for your exact machine, including system RAM, a different quantisation or a longer context? Use the hardware checker.
from nightmedia/Qwen3.5-9B-DS9-USS-Defiant
from ornith-ai/Ornith-1.5-9B
from DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED
from Qwen/Qwen3-VL-8B-Instruct
from Qwen/Qwen3.5-9B
from Qwen/Qwen3.5-9B
from XHToken/Spark-X2.5-4B
from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
from Qwen/Qwen2.5-VL-7B-Instruct
from ornith-ai/Ornith-1.5-9B
from empero-ai/Qwythos-9B-v2
from Qwen/Qwen3.5-4B
from empero-ai/Qwythos-9B-Claude-Mythos-5-1M
from Qwen/Qwen3.5-4B
from Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
from Qwen/Qwen3-8B
from empero-ai/Qwen3.8-9B-Distill
from Qwen/Qwen3.5-9B
from Qwen/Qwen2.5-Coder-7B-Instruct
from Qwen/Qwen3-0.6B
from bruhmoment4242/Qwen3-0.6B-Heretic
from Qwen/Qwen3-0.6B
from LiquidAI/LFM3-1.7B
from Qwen/Qwen2.5-7B-Instruct
from allura-forge/Llama-3.3-8B-Instruct
from meta-llama/Llama-3.2-3B-Instruct
from meta-llama/Llama-3.1-8B-Instruct
from empero-ai/Qwythos-9B-Claude-Mythos-5-1M
from Qwen/Qwen3-VL-4B-Instruct
from aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
from Qwen/Qwen3.5-2B
from Qwen/Qwen2.5-7B-Instruct
from Qwen/Qwen3.5-4B
from Qwen/Qwen3-0.6B-Base
from Qwen/Qwen3-8B
from Qwen/Qwen3.5-9B
from Qwen/Qwen3.5-9B
from nuofang/Qwen3.8-9B-Distill-SLERP-F451-Pro-Writer-Uncensored
from Qwen/Qwen3-8B-Base
from Qwen/Qwen2.5-7B-Instruct
from Tongyi-MAI/Z-Image-Turbo
from google/gemma-2-2b-it
from XHToken/Spark-X2.6-4B
from Qwen/Qwen3.5-9B
from Qwen/Qwen3-4B-Instruct-2507
from ornith-ai/Ornith-1.5-9B
from mlabonne/Qwen3-8B-abliterated
from black-forest-labs/FLUX.2-klein-9B
from Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
from Qwen/Qwen2.5-3B-Instruct
from meta-llama/Llama-3.2-3B-Instruct
from Qwen/Qwen2.5-Coder-7B-Instruct
from prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2
from Qwen/Qwen3-VL-8B-Instruct
from black-forest-labs/FLUX.2-klein-4B
from Qwen/Qwen3-4B
from Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
from Qwen/Qwen3.5-9B
from LiquidAI/LFM3-1.7B
from trohrbaugh/Qwen3.5-9B-heretic-v2
from mlabonne/Daredevil-8B-abliterated
from coder3101/Qwen3-VL-8B-Instruct-heretic
from Qwen/Qwen2.5-VL-3B-Instruct
from Qwen/Qwen3.5-2B
from google/gemma-3-1b-it
from Qwen/Qwen2.5-Coder-1.5B-Instruct
from QuixiAI/WizardLM-7B-Uncensored
from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
from Qwen/Qwen3.5-9B-Base
from MuXodious/Qwen3.5-4B-ARA-heresy-v2
from Qwen/Qwen2.5-Coder-3B-Instruct
from deepseek-ai/DeepSeek-R1-Distill-Llama-8B
from Orenguteng/Llama-3-8B-Lexi-Uncensored
from openbmb/MiniCPM-V-4.7-1B
from DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B
from meta-llama/Llama-3.2-1B-Instruct
from google/gemma-2-9b-it
from ornith-ai/Ornith-1.0-9B
from AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF
from AyoubChLin/lfm2.5-2.6b-fable5-coding-agent
from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
from Qwen/Qwen3-4B
from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
from deepreinforce-ai/Ornith-1.0-9B
from prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX
from empero-ai/Qwen3.8-4B-Distill
from dphn/Dolphin3.0-Llama3.1-8B
from Qwen/Qwen2.5-Coder-1.5B-Instruct
from Qwen/Qwen3.5-4B
from empero-ai/Qwen3.8-4B-Distill
from Qwen/Qwen3.5-0.8B
from ornith-ai/Ornith-1.5-9B
from huihui-ai/Huihui-Qwen3.5-0.8B-abliterated
from IlyaGusev/gemma-2-9b-it-abliterated
from openbmb/MiniCPM5-2B
from coder3101/Qwen3.5-4B-heretic
from meta-llama/Llama-3.2-3B
from 01-ai/Yi-1.5-9B-Chat-16K
from DavidAU/Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking
from Qwen/Qwen3-VL-8B-Instruct
from DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3
from DavidAU/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP
from Orenguteng/Llama-3-8B-Lexi-Uncensored
from mlabonne/Qwen3-4B-abliterated
from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
from Qwen/Qwen3.5-9B
from Qwen/Qwen2.5-3B-Instruct
from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
from prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX
from trohrbaugh/Qwen3.5-9B-heretic-v2
from Qwen/Qwen2.5-1.5B-Instruct
from 01-ai/Yi-1.5-9B-Chat
Showing the 120 most-downloaded of 278 models in this group. The remaining 158 are reachable through the full paginated index and are all listed in the sitemap.