Models

nemotron-cascade-2

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

dlasher/Nemotron-Cascade-2-30B-A3B-GGUF

requant to IQ4_NL, with combined_en_huge as prompt (English + Coding focus)

dlasher/Nemotron-Cascade-2-30B-A3B

pulled as BF16, requant to IQ4_NL, with combined_en_huge as dataset (English + Coding focus)

gag0/Nemotron-Cascade-2-30B-A3B