Parable-Nanbeige4.2-3B-Claude-Fable-5-heretic
An abliterated (refusal-suppressed) version of AnkitAI/Parable-Nanbeige4.2-3B-Claude-Fable-5, produced with Heretic via directional ablation / weight orthogonalization. Refusals drop from...
Метка: reasoning
Parable-Nanbeige4.2-3B-Claude-Fable-5
Part of the Parable series: small local LLMs fine-tuned on genuine agent traces. This is the reasoning-style chat...
empero-ai_Qwythos-9B-v2-GGUF
Original model: https://huggingface.co/empero-ai/Qwythos-9B-v2 — llama.cpp — ramalama — LM Studio — koboldcpp — Jan AI — Text Generation...
Gemma-4-31B-Isometry-Fabled-Persona
This is a reasoning-first, agentic and conversational merge of google/gemma-4-31B-it. It has enough creative and roleplay tuning to...
Hy3-JANG_2K-MTP
Quantized tencent/Hy3 for Apple Silicon MLX / JANG runtimes — a 295B-total / 21B-active text MoE, packed to...
Pantheon-Reasoning-26B-A4B-1.1-heretic
An experiment in bringing reasoning capability to the Pantheon roleplay series in the shape of a Gemma 4...
fabletron-nemotron-3-super-120b-BF16
QLoRA fine-tune of NVIDIA Nemotron-3-Super-120B-A12B (120B-total / 12B-active hybrid Mamba-2 + Latent-MoE, nemotronh) on the piagent split of...
YuYu1015-Ornith-1.0-9B-abliterated-dpo
> | repeat-penalty 1.05 ✅ | correct (sweet spot) | > | repeat-penalty 1.0 | severe thinking loops...
Qwen3-4B-Thinking-2507
LiteRT is Google’s on-device runtime, the new name for TensorFlow Lite (Android: com.google.ai.edge.litert:litert), and litert-torch, the renamed ai-edge-torch,...
Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16
This repository contains a bfloat16 MLX conversion of empero-ai/Qwythos-9B-Claude-Mythos-5-1M for Apple Silicon inference with MLX, MLX-LM, MLX-VLM, and...