Janus-35B-HERETIC
> Flagship Reasoning. Sparse Footprint. Uncensored. > llmfan46’s Heretic abliteration of Qwen 3.6 35B-A3B, repackaged with Claude Fable...
> Flagship Reasoning. Sparse Footprint. Uncensored. > llmfan46’s Heretic abliteration of Qwen 3.6 35B-A3B, repackaged with Claude Fable...
Part of the CoNDeNse project — compressing the reasoning capability of large models into small, deployable ones. —...
Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed...
A fine-tune of NVIDIA’s Nemotron-3-Nano-30B-A3B (31.6B-parameter hybrid Mamba-2 + MoE + Attention, thinking-capable) that does one thing: turn...
Nomi-1.1 is a refined mid-range Large Language Model based on the Llama-3.2-3B architecture. It was specifically developed to...
GGUF quantized versions of AYI-NEDJIMI/ISO27001-Expert-1.5B for use with Ollama, llama.cpp, LM Studio, and other GGUF-compatible inference engines. This...
Logic Reasoner v2 is a verdict-style reasoning and verification model packaged for Ollama and distributed as GGUF. It...
Формат GGUF distil-qwen3-4b-text2sql для локального вывода с Ollama, llama.cpp и другими GGUF-совместимыми инструментами. Для меньшей загрузки см. 4-разрядную...
Bu depo, Türkçe akıl yürütme (Цепь мыслей) yetenekleri kazandırılmış Gemma3-4B dil modelinin değerlendirme süreçlerini, istemlerini (подсказки) ve kullanım...
A cutting-edge 350M parameter AI model with a dedicated Android runtime for immersive RolePlay experiences YutaLM v1.0 DEMO...