Darkmere-8B-v0.1 · mradermacher

Darkmere-8B-v0.1 I1-IQ2_XS

This file is exactly 2,745,996,736 bytes — 2.56 GiB / 2.75 GB at an effective 2.588 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

2.56 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Darkmere-8B-v0.1-i1-GGUF:I1-IQ2_XS

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

Hugging Face CLI

hf download mradermacher/Darkmere-8B-v0.1-i1-GGUF Darkmere-8B-v0.1.i1-IQ2_XS.gguf

Direct download

Darkmere-8B-v0.1.i1-IQ2_XS.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

2.56 GiB

2.75 GB

Effective bpw

2.588

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata