MultiverseComputingCAI/Pulsar-16B-BF16

Different architecture vs nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. Different architecture: only 125 of 6243/4041 tensors match by name and shape.

2 derivatives checked

• mradermacher/Pulsar-16B-BF16-i1-GGUF: Quantization
• mradermacher/Pulsar-16B-BF16-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse