Views
No views yet
1# Convert HF model to GGUF (bf16)
2python llama.cpp/convert_hf_to_gguf.py \
3 nvidia/Nemotron-Cascade-2-30B-A3B \
4 --outfile Nemotron-Cascade-2-30B-A3B-bf16.gguf \
5 --outtype bf16
6
7# Quantize to Q4_K_M
8llama-quantize Nemotron-Cascade-2-30B-A3B-bf16.gguf \
9 Nemotron-Cascade-2-30B-A3B-Q4_K_M.gguf Q4_K_M