GraySoft
Model Comparison

jiunsong/supergemma4-26b-uncensored-gguf-v2vsmradermacher/assistant_pepe_70b-i1-gguf

Side-by-side comparison of jiunsong/supergemma4-26b-uncensored-gguf-v2 and mradermacher/assistant_pepe_70b-i1-gguf: downloads, license, context length, tasks, and benchmarks.

jiunsong/supergemma4-26b-uncensored-gguf-v2

Jiunsong · text-generation

The fast, uncensored llama.cpp build of the strongest SuperGemma text line. This release is for people who want three things together:

mradermacher/assistant_pepe_70b-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_70B ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Assistant_Pepe_70B-GGUF

Side-by-side Specifications

jiunsong/supergemma4-26b-uncensored-gguf-v2mradermacher/assistant_pepe_70b-i1-gguf
AuthorJiunsongmradermacher
Pipeline Tasktext-generation
Librarytransformers
Downloads42,46832,959
Likes3361
LicenseUnknownUnknown
Context Length
Created2026-04-112026-04-02
Last Modified2026-04-122026-04-03
Tags
ggufgemma4uncensoredfastllama.cppapple-siliconconversationalkoreancodingtool-use
transformersggufendataset:SicariusSicariiStuff/UBW_Tapestriesbase_model:SicariusSicariiStuff/Assistant_Pepe_70Bbase_model:quantized:SicariusSicariiStuff/Assistant_Pepe_70Blicense:llama3.1endpoints_compatibleregion:usimatrix

View full details: jiunsong/supergemma4-26b-uncensored-gguf-v2 · mradermacher/assistant_pepe_70b-i1-gguf