MiniMax M2.7 ultra uncensored heretic is Out Now with 4/100 Refusals, Available in Safetensors and GGUFs Formats!
Summary
The MiniMax M2.7 model has been fine-tuned into an uncensored variant, 'ultra uncensored heretic', with very low refusal rates (4/100). Available in Safetensors and GGUF formats on HuggingFace.
Similar Articles
Qwen3.6 35B A3B uncensored heretic Native MTP Preserved is Out Now With KLD 0.0015, 10/100 Refusals and the Full 19 MTPs Preserved and Retained, Available in Safetensors, GGUFs. NVFP4, NVFP4 GGUFs and GPTQ-Int4 Formats
Community release of Qwen3.6 35B A3B uncensored variant with full 19 MTP tensors preserved, available in multiple formats including Safetensors, GGUF, NVFP4 and GPTQ-Int4.
G4-Meromero-31B-Uncensored-Heretic Is Out Now, a Finetune of Gemma 4 31B It Designed for Creative Tasks, With Kld of 0.0100 and 15/100 Refusals!
G4-Meromero-31B-Uncensored-Heretic is a finetune of Gemma 4 31B that reduces refusal rate to 15/100 while keeping KL divergence at 0.01, preserving model quality. It is designed for creative tasks and available as GGUF quantizations on Hugging Face.
@stevibe: MiniMax M2.7 is 230B params. Can you actually run it at home? I tested Unsloth's UD-IQ3_XXS (80GB) on 4 different rigs:…
A user tested MiniMax M2.7 (230B parameter model) using Unsloth's UD-IQ3_XXS quantization (80GB) across four different hardware configurations including RTX 4090, RTX 5090, RTX PRO 6000, and DGX setups, reporting token generation speeds and time-to-first-token metrics.
@0x0SojalSec: SUPER GEMMA 4 26B UNCENSORED GGUF v2 IS INSANE, - 0/100 refusals (actually uncensored) - Fixed all the tool-call + toke…
Super Gemma 4 26B Uncensored GGUF v2 is a community fine-tuned model offering uncensored responses with zero refusals, improved speed, and fixed tool-calling, optimized for local inference on llama.cpp and vLLM.
@no_stp_on_snek: After testing a replay of prompts from this model I can confidently say it's a viable replacement for one of my product…
A decensored version of Qwen3.6-35B-A3B, using the Heretic method with MPOA, achieving 88% fewer refusals while preserving model quality, is released as GGUF quantizations by llmfan46.