gemma-4-26B-roleplay-v2-merged I1-Q2_K_S

This file is exactly 10,624,481,568 bytes — 9.89 GiB / 10.62 GB at an effective 3.368 bits per weight. The nominal rate for I1-Q2_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

9.89 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/gemma-4-26B-roleplay-v2-merged-i1-GGUF:I1-Q2_K_S

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

Hugging Face CLI
hf download mradermacher/gemma-4-26B-roleplay-v2-merged-i1-GGUF gemma-4-26B-roleplay-v2-merged.i1-Q2_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
9.89 GiB
10.62 GB
Effective bpw
3.368
from real bytes ÷ params
Tensors
Header
GGUF metadata
gemma-4-26B-roleplay-v2-merged I1-Q2_K_S — exact size and VRAM — ossmodeldb