LTX-2.3 · unsloth

LTX-2.3 Q3_K_M

This file is exactly 10,629,508,128 bytes — 9.90 GiB / 10.63 GB at an effective 9.246 bits per weight. The nominal rate for Q3_K_M 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

9.90 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/LTX-2.3-GGUF:Q3_K_M

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

Hugging Face CLI
hf download unsloth/LTX-2.3-GGUF distilled-1.1/ltx-2.3-22b-distilled-1.1-Q3_K_M.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
9.90 GiB
10.63 GB
Effective bpw
9.246
from real bytes ÷ params
Tensors
4444
Header
0.38 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
2672
Q3_K
1376
Q4_K
366
BF16
28
Q5_K
2

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.