GraySoft
Download guIDE →
Model Comparison

mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-ggufvsunsloth/gemma-4-26b-a4b-it-gguf

Side-by-side comparison of mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-gguf and unsloth/gemma-4-26b-a4b-it-gguf: downloads, license, context length, tasks, and benchmarks.

mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/trohrbaugh/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-heretic ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/NVIDIA-…

unsloth/gemma-4-26b-a4b-it-gguf

unsloth · image-text-to-text

processor = AutoProcessor.from_pretrained(MODEL_ID) model = AutoModelForCausalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto" ) `` Once the model is loaded, you can start generating output: `python # Prompt messages = [ {"role": "system", "content": "You are a help…

Side-by-side Specifications

mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-ggufunsloth/gemma-4-26b-a4b-it-gguf
Authormradermacherunsloth
Pipeline Task—image-text-to-text
Librarytransformers—
Downloads22,2152,104,448
Likes2492
LicenseUnknownUnknown
Context Length——
Created2026-03-182026-04-01
Last Modified2026-03-192026-04-11
Tags
transformersggufnvidiapytorchnemotron-3latent-moemtphereticuncensoreddecensored
ggufgemma4unslothgemmagoogleimage-text-to-textbase_model:google/gemma-4-26B-A4B-itbase_model:quantized:google/gemma-4-26B-A4B-itlicense:apache-2.0endpoints_compatible

View full details: mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-gguf · unsloth/gemma-4-26b-a4b-it-gguf