GPT-OSS-Cybersecurity-20B-Merged-heretic I1-IQ3_XXS

This file is exactly 12,065,516,384 bytes — 11.24 GiB / 12.07 GB at an effective 4.615 bits per weight. The nominal rate for I1-IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

11.24 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/GPT-OSS-Cybersecurity-20B-Merged-heretic-i1-GGUF:I1-IQ3_XXS

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

Hugging Face CLI
hf download mradermacher/GPT-OSS-Cybersecurity-20B-Merged-heretic-i1-GGUF GPT-OSS-Cybersecurity-20B-Merged-heretic.i1-IQ3_XXS.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
11.24 GiB
12.07 GB
Effective bpw
4.615
from real bytes ÷ params
Tensors
Header
GGUF metadata
GPT-OSS-Cybersecurity-20B-Merged-heretic I1-IQ3_XXS — exact size and VRAM — ossmodeldb