Modelpublic

minjaechoi/nemotron3-nano-30b-a3b-2p03bit-r34

sourceHugging Faceupdated 5d agoView on Hugging Face

0likes162downloads

Model Card

NVIDIA-Nemotron-3-Nano-30B-A3B — 2-bit routed experts (r34)

Internal research checkpoint. Routed experts average 2.025 bits; every other weight is BF16. Weights are stored dequantized in BF16 tensors and load with stock transformers / vLLM.


Base model	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Routed-expert average	2.025 bits
Internal ID	r34

License follows the base model.