LTX2.3-10Eros · vantagewithai
LTX2.3-10Eros Q8_0
This file is exactly 22,755,564,896 bytes — 21.19 GiB / 22.76 GB at an effective 8.667 bits per weight. The nominal rate for Q8_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
21.19 GiB · 1 file
llama.cpp
llama-cli -hf vantagewithai/LTX2.3-10Eros-1.4-GGUF:Q8_0
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download vantagewithai/LTX2.3-10Eros-1.4-GGUF 10Eros_v1.4-Q8_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.
Size
21.19 GiB
22.76 GB
Effective bpw
8.667
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
Q8_0
1744
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.