Llama-3-8B-Instruct-32k-v0.1 · MaziyarPanahi

Llama-3-8B-Instruct-32k-v0.1 IQ4_XS

This file is exactly 4,447,662,592 bytes — 4.14 GiB / 4.45 GB at an effective 4.431 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 291 tensors parsed

Get it

4.14 GiB · 1 file
llama.cpp
llama-cli -hf MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF:IQ4_XS

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

Hugging Face CLI
hf download MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF Llama-3-8B-Instruct-32k-v0.1.IQ4_XS.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.

Repository →
Size
4.14 GiB
4.45 GB
Effective bpw
4.431
from real bytes ÷ params
Tensors
291
Header
7.84 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
IQ4_XS
193
F32
65
Q5_K
32
Q6_K
1

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.