LTX2.3-10Eros · vantagewithai

LTX2.3-10Eros Q4_0

This file is exactly 12,980,918,688 bytes — 12.09 GiB / 12.98 GB at an effective 4.944 bits per weight. The nominal rate for Q4_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 4444 tensors parsed

Get it

12.09 GiB · 1 file
llama.cpp
llama-cli -hf vantagewithai/LTX2.3-10Eros-GGUF:Q4_0

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

Hugging Face CLI
hf download vantagewithai/LTX2.3-10Eros-GGUF 10Eros_v1-Q4_0.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
12.09 GiB
12.98 GB
Effective bpw
4.944
from real bytes ÷ params
Tensors
4444
Header
0.40 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
2672
Q4_0
1482
Q5_K
204
Q4_1
58
BF16
28

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.