Merged-RP-Stew-V2-51B · mradermacher

Merged-RP-Stew-V2-51B I1-Q5_K_S

This file is exactly 35,214,927,712 bytes — 32.80 GiB / 35.21 GB at an effective 5.510 bits per weight. The nominal rate for I1-Q5_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

32.80 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF:I1-Q5_K_S

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF Merged-RP-Stew-V2-51B.i1-Q5_K_S.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
32.80 GiB
35.21 GB
Effective bpw
5.510
from real bytes ÷ params
Tensors
Header
GGUF metadata
Merged-RP-Stew-V2-51B I1-Q5_K_S — exact size and VRAM — ossmodeldb