GraySoft
Download guIDE →
Model Comparison

noctrex/gemma-4-26b-a4b-it-mxfp4_moe-ggufvsunsloth/deepseek-r1-distill-llama-70b-gguf

Side-by-side comparison of noctrex/gemma-4-26b-a4b-it-mxfp4_moe-gguf and unsloth/deepseek-r1-distill-llama-70b-gguf: downloads, license, context length, tasks, and benchmarks.

noctrex/gemma-4-26b-a4b-it-mxfp4_moe-gguf

noctrex · image-text-to-text

These are **MXFP4** quantizations of the model gemma-4-26B-A4B-it

unsloth/deepseek-r1-distill-llama-70b-gguf

unsloth · text-generation

We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb

Side-by-side Specifications

noctrex/gemma-4-26b-a4b-it-mxfp4_moe-ggufunsloth/deepseek-r1-distill-llama-70b-gguf
Authornoctrexunsloth
Pipeline Taskimage-text-to-texttext-generation
Library—transformers
Downloads19,21420,715
Likes10110
LicenseUnknownUnknown
Context Length——
Created2026-04-022025-01-20
Last Modified2026-04-122025-05-10
Tags
ggufimage-text-to-textbase_model:google/gemma-4-26B-A4B-itbase_model:quantized:google/gemma-4-26B-A4B-itendpoints_compatibleregion:usconversational
transformersggufllamatext-generationdeepseekunslothllama-3metaenarxiv:2501.12948

View full details: noctrex/gemma-4-26b-a4b-it-mxfp4_moe-gguf · unsloth/deepseek-r1-distill-llama-70b-gguf