Bielik-11B-v2.2-Instruct · bartowski

Bielik-11B-v2.2-Instruct IQ3_M

This file is exactly 5,038,780,704 bytes — 4.69 GiB / 5.04 GB at an effective 3.609 bits per weight. The nominal rate for IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

4.69 GiB · 1 file

llama.cpp

llama-cli -hf bartowski/Bielik-11B-v2.2-Instruct-GGUF:IQ3_M

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

Hugging Face CLI

hf download bartowski/Bielik-11B-v2.2-Instruct-GGUF Bielik-11B-v2.2-Instruct-IQ3_M.gguf

Direct download

Bielik-11B-v2.2-Instruct-IQ3_M.gguf

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.

Repository →

Size

4.69 GiB

5.04 GB

Effective bpw

3.609

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata