GraySoft
Model Comparison

liquidai/lfm2.5-1.2b-thinking-ggufvsllmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf

Side-by-side comparison of liquidai/lfm2.5-1.2b-thinking-gguf and llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf: downloads, license, context length, tasks, and benchmarks.

liquidai/lfm2.5-1.2b-thinking-gguf

LiquidAI · text-generation

LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking

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

Side-by-side Specifications

liquidai/lfm2.5-1.2b-thinking-ggufllmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf
AuthorLiquidAIllmfan46
Pipeline Tasktext-generationimage-text-to-text
Librarytransformers
Downloads49,50324,684
Likes8517
LicenseUnknownUnknown
Context Length
Created2026-01-162026-03-10
Last Modified2026-04-062026-03-27
Tags
ggufliquidlfm2.5edgellama.cpptext-generationenarzhfr
transformersggufhereticuncensoreddecensoredabliteratedimage-text-to-textarxiv:1905.07830arxiv:1905.10044arxiv:1911.11641

View full details: liquidai/lfm2.5-1.2b-thinking-gguf · llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf