ACE-Step-v1-5-XL-DiT-Base · scragnog
ACE-Step-v1-5-XL-DiT-Base Q4_K_M
This file is exactly 11,959,690,752 bytes — 11.14 GiB / 11.96 GB at an effective 19.180 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 4 file(s), summed
Get it
11.14 GiB · 4 files
llama.cpp
llama-cli -hf scragnog/ace-step-1.5-gguf-merge-models:Q4_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download scragnog/ace-step-1.5-gguf-merge-models --include "acestep-v15-merge-base-sft-xl-ta-0.5-Q4_K_M.gguf"
This quantization is split across 4 files totalling 11.14 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 4 required
- acestep-v15-merge-base-sft-xl-ta-0.5-Q4_K_M.gguf
- acestep-v15-merge-base-turbo-xl-ta-0.5-Q4_K_M.gguf
- acestep-v15-merge-sft-turbo-xl-ta-0.3-Q4_K_M.gguf
- acestep-v15-merge-sft-turbo-xl-ta-0.7-Q4_K_M.gguf
Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.
Size
11.14 GiB
11.96 GB
Effective bpw
19.180
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata