GraySoft
Model Comparison

llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-ggufvstvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf

Side-by-side comparison of llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf and tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf: downloads, license, context length, tasks, and benchmarks.

llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf

llmfan46 · image-text-to-text

GGUF quantizations of llmfan46/gemma-3-12b-it-ultra-uncensored-heretic. # This is a decensored version of google/gemma-3-12b-it, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf

tvall43 · text-generation

can i fit moe qwen3.5 in 10gb vram? since thats already risky, lets yolo and use claude distil too. 0.65 compression this time. my original goal was 8gb vram but i mathed wrong somewhere. that fits fine on my gpro x080 but not single gpu in the radeon v340l. maybe ill give it an…

Side-by-side Specifications

llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguftvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf
Authorllmfan46tvall43
Pipeline Taskimage-text-to-texttext-generation
Librarytransformerstransformers
Downloads24,68420,490
Likes1718
LicenseUnknownUnknown
Context Length
Created2026-03-102026-03-09
Last Modified2026-03-272026-03-09
Tags
transformersggufhereticuncensoreddecensoredabliteratedimage-text-to-textarxiv:1905.07830arxiv:1905.10044arxiv:1911.11641
transformersgguftext-generation-inferenceunslothqwen3_5_moeqwenqwen3.5reasoningchain-of-thoughttext-generation

View full details: llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf · tvall43/qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-gguf