GraySoft
Model Comparison

mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-ggufvsunsloth/qwen3-1.7b-gguf

Side-by-side comparison of mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-gguf and unsloth/qwen3-1.7b-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/qwen3-1.7b-gguf

unsloth · text-generation

If you are using llama.cpp, Ollama, Open WebUI etc., you can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of mu…

Side-by-side Specifications

mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-ggufunsloth/qwen3-1.7b-gguf
Authormradermacherunsloth
Pipeline Tasktext-generation
Librarytransformerstransformers
Downloads22,21522,966
Likes266
LicenseUnknownUnknown
Context Length
Created2026-03-182025-04-28
Last Modified2026-03-192025-06-08
Tags
transformersggufnvidiapytorchnemotron-3latent-moemtphereticuncensoreddecensored
transformersggufqwen3text-generationqwenunslothenbase_model:Qwen/Qwen3-1.7Bbase_model:quantized:Qwen/Qwen3-1.7Blicense:apache-2.0

View full details: mradermacher/nvidia-nemotron-3-super-120b-a12b-bf16-heretic-i1-gguf · unsloth/qwen3-1.7b-gguf