Modelpublic

minjaechoi/nemotron3-nano-30b-a3b-tileq-2p30bit-r43

sourceHugging Faceupdated 4d agoView on Hugging Face

0likes97downloads

Model Card

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 — 2.3010-bit routed experts (r43)

Internal research checkpoint. Routed experts average 2.3010 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	2.3010 bits
Internal ID	r43

License follows the base model.