Qwen3.8 27B Uncensored / Abliterated Collection Abliterated (refusal-removed) Qwen3.8-27B in every format: BF16, FP8, NVFP4, INT8, GGUF, MLX, plus the 15.7 GB OrcaSAQ2 GGUF. Research use only. • 8 items • Updated 6 days ago • 114
Qwen3.8 Flash Next Uncensored / Abliterated Collection Abliterated Qwen3.8-Flash-Next, a Qwen4-architecture MoE with vision, tools and thinking: BF16, FP8, NVFP4, GGUF and MLX. Research use only. • 5 items • Updated 6 days ago • 19
💧 LFM3 Collection Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3). • 7 items • Updated 21 days ago • 317
Conjunctive Backdoor Organisms Collection Conjunctive (AND) backdoor organisms and single-trigger controls on Gemma-2, Qwen2.5 and Llama-3, over size, trigger count and behavior. • 86 items • Updated 22 days ago • 1
K2 Horizon Collection K2 Horizon models, datasets, and supporting resources • 14 items • Updated 1 day ago • 158