meteor-v4-2048 · mradermacher

meteor-v4-2048 I1-IQ2_S

This file is exactly 3,211,487,552 bytes — 2.99 GiB / 3.21 GB at an effective 2.780 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

2.99 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/meteor-v4-2048-i1-GGUF:I1-IQ2_S

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

Hugging Face CLI
hf download mradermacher/meteor-v4-2048-i1-GGUF meteor-v4-2048.i1-IQ2_S.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
2.99 GiB
3.21 GB
Effective bpw
2.780
from real bytes ÷ params
Tensors
Header
GGUF metadata
meteor-v4-2048 I1-IQ2_S — exact size and VRAM — ossmodeldb