GraySoft
Model Comparison

liquidai/lfm2-24b-a2b-ggufvsllmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf: downloads, license, context length, tasks, and benchmarks.

liquidai/lfm2-24b-a2b-gguf

LiquidAI · text-generation

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient. !image Find more information about LFM2-24B-A2B in our blog post.

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/lfm2-24b-a2b-ggufllmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf
AuthorLiquidAIllmfan46
Pipeline Tasktext-generationimage-text-to-text
Librarytransformerstransformers
Downloads56,74824,684
Likes12217
LicenseUnknownUnknown
Context Length
Created2026-02-172026-03-10
Last Modified2026-03-302026-03-27
Tags
transformersggufliquidlfm2edgemoellama.cpptext-generationenar
transformersggufhereticuncensoreddecensoredabliteratedimage-text-to-textarxiv:1905.07830arxiv:1905.10044arxiv:1911.11641

View full details: liquidai/lfm2-24b-a2b-gguf · llmfan46/gemma-3-12b-it-ultra-uncensored-heretic-gguf