Athene-Phi-3.5-mini-instruct-orpo · mradermacher

Athene-Phi-3.5-mini-instruct-orpo I1-IQ2_S

This file is exactly 2,516,410,432 bytes — 2.34 GiB / 2.52 GB at an effective 5.269 bits per weight. The nominal rate for I1-IQ2_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

2.34 GiB · 2 files

llama.cpp

llama-cli -hf mradermacher/Athene-Phi-3.5-mini-instruct-orpo-i1-GGUF:I1-IQ2_S

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

Hugging Face CLI

hf download mradermacher/Athene-Phi-3.5-mini-instruct-orpo-i1-GGUF --include "Athene-Phi-3.5-instruct.i1-IQ2_S.gguf"

This quantization is split across 2 files totalling 2.34 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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

2.34 GiB

2.52 GB

Effective bpw

5.269

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata