GraySoft
Model Comparison

jiunsong/supergemma4-26b-uncensored-gguf-v2vsmradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf

Side-by-side comparison of jiunsong/supergemma4-26b-uncensored-gguf-v2 and mradermacher/minimax-m2.5-carve-v1-bf16-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/minimax-m2.5-carve-v1-bf16-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/vpyn/MiniMax-M2.5-CARVE-v1-BF16 ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/MiniMax-M2.5-CARVE-v1-BF16-GGUF

Side-by-side Specifications

jiunsong/supergemma4-26b-uncensored-gguf-v2mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf
AuthorJiunsongmradermacher
Pipeline Tasktext-generation
Librarytransformers
Downloads42,46822,565
Likes3360
LicenseUnknownUnknown
Context Length
Created2026-04-112026-03-25
Last Modified2026-04-122026-03-30
Tags
ggufgemma4uncensoredfastllama.cppapple-siliconconversationalkoreancodingtool-use
transformersggufenbase_model:vpyn/MiniMax-M2.5-CARVE-v1-BF16base_model:quantized:vpyn/MiniMax-M2.5-CARVE-v1-BF16endpoints_compatibleregion:usimatrixconversational

View full details: jiunsong/supergemma4-26b-uncensored-gguf-v2 · mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf