rwkv7-g1 · RemySkye
rwkv7-g1 I1-IQ4_NL
This file is exactly 8,388,165,856 bytes — 7.81 GiB / 8.39 GB at an effective 5.057 bits per weight. The nominal rate for I1-IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
7.81 GiB · 1 file
llama.cpp
llama-cli -hf RemySkye/rwkv7-g1h-13.3b-i1-GGUF:I1-IQ4_NL
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download RemySkye/rwkv7-g1h-13.3b-i1-GGUF rwkv7-g1h-13.3b-20260710-ctx10240.i1-IQ4_NL.gguf
Direct download
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
7.81 GiB
8.39 GB
Effective bpw
5.057
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata