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 about 5 hours ago • 112
Ornith-1.0 Collection Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated Sep 20 • 394
Qwen-3.6-unsloth-mlx Collection AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 18 items • Updated May 15 • 19
🎯 Liquid Nanos Collection Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 38 items • Updated 15 days ago • 140