GraySoft
Model Comparison

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufvsunsloth/gemma-3-12b-it-qat-gguf

Side-by-side comparison of failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf and unsloth/gemma-3-12b-it-qat-gguf: downloads, license, context length, tasks, and benchmarks.

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf

failspy · —

# Llama-3-70B-Instruct-abliterated-v3.5 Model Card My original Jupyter "cookbook" to replicate the methodology can be found here My personal library o' code used (WIP, looking to improve and generalize) This is meta-llama/Meta-Llama-3-70B-Instruct with orthogonalized bfloat16 sa…

unsloth/gemma-3-12b-it-qat-gguf

unsloth · image-text-to-text

**Model Page**: Gemma > [!Note] > This repository corresponds to the 12B **instruction-tuned** version of the Gemma 3 model using Quantization Aware Training (QAT). > > **The checkpoint in this repository is unquantized, please make sure to quantize with Q4_0 with your favorite …

Side-by-side Specifications

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufunsloth/gemma-3-12b-it-qat-gguf
Authorfailspyunsloth
Pipeline Taskimage-text-to-text
Librarytransformerstransformers
Downloads36,98229,663
Likes2543
LicenseUnknownUnknown
Context Length
Created2024-05-282025-04-21
Last Modified2024-05-302025-05-12
Tags
transformersgguflicense:llama3endpoints_compatibleregion:usconversational
transformersggufgemma3image-text-to-textunslothgemmagooglearxiv:1905.07830arxiv:1905.10044arxiv:1911.11641

View full details: failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf · unsloth/gemma-3-12b-it-qat-gguf