llmfan46/qwen3.5-35b-a3b-ultra-uncensored-heretic-ggufvsunsloth/llama-3.2-1b-instruct-gguf
Side-by-side comparison of llmfan46/qwen3.5-35b-a3b-ultra-uncensored-heretic-gguf and unsloth/llama-3.2-1b-instruct-gguf: downloads, license, context length, tasks, and benchmarks.
llmfan46/qwen3.5-35b-a3b-ultra-uncensored-heretic-gguf
GGUF quantizations of llmfan46/Qwen3.5-35B-A3B-heretic-v2. # This is a decensored version of Qwen/Qwen3.5-35B-A3B, made using Heretic v1.2.0 with Magnitude-Preserving Orthogonal Ablation (MPOA) and Self-Organizing Map Abliteration (SOMA)
unsloth/llama-3.2-1b-instruct-gguf
16bit, 8bit, 6bit, 5bit, 4bit, 3bit and 2bit uploads avaliable. # Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth! We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXH…
Side-by-side Specifications
| llmfan46/qwen3.5-35b-a3b-ultra-uncensored-heretic-gguf | unsloth/llama-3.2-1b-instruct-gguf | |
|---|---|---|
| Author | llmfan46 | unsloth |
| Pipeline Task | image-text-to-text | text-generation |
| Library | — | transformers |
| Downloads | 36,377 | 64,318 |
| Likes | 54 | 58 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2026-03-03 | 2024-09-25 |
| Last Modified | 2026-04-10 | 2025-05-09 |
| Tags |
View full details: llmfan46/qwen3.5-35b-a3b-ultra-uncensored-heretic-gguf · unsloth/llama-3.2-1b-instruct-gguf