Qwen3-VL-12B-Instruct-Brainstorm20x I1-IQ2_XS

This file is exactly 3,782,187,744 bytes — 3.52 GiB / 3.78 GB at an effective 2.552 bits per weight. The nominal rate for I1-IQ2_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

3.52 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF:I1-IQ2_XS

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

Hugging Face CLI
hf download mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF Qwen3-VL-12B-Instruct-Brainstorm20x.i1-IQ2_XS.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
3.52 GiB
3.78 GB
Effective bpw
2.552
from real bytes ÷ params
Tensors
Header
GGUF metadata