HackerTwins/NVIDIA-Nemotron-Labs-3-Elastic-23B-A2.8B-GGUF

NVIDIA Nemotron Labs 3 Elastic 23B A2.8B GGUF

Tiny enough to squeeze onto real hardware. Big enough to be interesting.

This repo contains GGUF 4-bit quantized files for running NVIDIA Nemotron Labs 3 Elastic 23B A2.8B with llama.cpp-compatible runtimes.

Files

Which one should I use?

Use Q4_K_S if you are trying to make this thing fit on a 16GB GPU.

Use Q4_K_M if you have around 20GB+ available memory and want the better 4-bit quant.

Use in LM Studio

Open LM Studio and search for:

HackerTwins/NVIDIA-Nemotron-Labs-3-Elastic-23B-A2.8B-GGUF

You can also paste this Hugging Face repo URL directly into LM Studio’s model search.

license: other licensename: nvidia-open-model-license licenselink: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ ---