Darkmere-8B-v0.1 · mradermacher

Darkmere-8B-v0.1 I1-IQ2_S

This file is exactly 2,904,593,856 bytes — 2.71 GiB / 2.90 GB at an effective 2.737 bits per weight. The nominal rate for I1-IQ2_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.71 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Darkmere-8B-v0.1-i1-GGUF:I1-IQ2_S

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_S.gguf

Direct download

Darkmere-8B-v0.1.i1-IQ2_S.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

2.71 GiB

2.90 GB

Effective bpw

2.737

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata