GraySoft
Model Comparison

dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fixvslmg-anon/vntl-llama3-8b-v2-gguf

Side-by-side comparison of dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix and lmg-anon/vntl-llama3-8b-v2-gguf: downloads, license, context length, tasks, and benchmarks.

dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix

Dampfinchen · —

https://huggingface.co/stduhpf/google-gemma-3-12b-it-qat-q4_0-gguf-small but with tokens 105 and 106 and their corresponding image tokens set to control instead of normal. Added general.name metadata.

lmg-anon/vntl-llama3-8b-v2-gguf

lmg-anon · translation

This is a LLaMA 3 Youko qlora fine-tune, created using a new version of the VNTL dataset. The purpose of this fine-tune is to improve performance of LLMs at translating Japanese visual novels to English. Unlike the previous version, this one doesn't includes the "chat mode".

Side-by-side Specifications

dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fixlmg-anon/vntl-llama3-8b-v2-gguf
AuthorDampfinchenlmg-anon
Pipeline Tasktranslation
Library
Downloads20,1491,522,503
Likes1113
LicenseUnknownUnknown
Context Length
Created2025-04-092025-01-02
Last Modified2025-04-092025-01-02
Tags
gguflicense:gemmaendpoints_compatibleregion:usconversational
gguftranslationjaendataset:lmg-anon/VNTL-v5-1kbase_model:rinna/llama-3-youko-8bbase_model:quantized:rinna/llama-3-youko-8blicense:llama3endpoints_compatibleregion:us

View full details: dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix · lmg-anon/vntl-llama3-8b-v2-gguf