The Bestiary Collection Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated 23 days ago • 69
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 22 days ago • 51
Granite Quantized Models Collection Quantized versions of IBM Granite models. Licensed under the Apache 2.0 license. • 44 items • Updated 18 days ago • 27
On Path to Multimodal Generalist: General-Level and General-Bench Paper • 2505.04620 • Published May 7 • 82
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated Jul 21 • 160
Josiefied and Abliterated Qwen3 Collection Abliterated, and further fine-tuned to be the most uncensored models available. • 17 items • Updated Nov 6 • 30
GGUF Image Model Quants Collection List of GGUF quants for text to image base models. • 31 items • Updated May 8 • 76
Thinking / Reasoning Models - Reg and MOEs. Collection QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 177 items • Updated about 8 hours ago • 14