Qwen3-VL-8B-NSFW-Caption-V4.5 · mradermacher

Qwen3-VL-8B-NSFW-Caption-V4.5 IQ4_XS

This file is exactly 4,593,298,528 bytes — 4.28 GiB / 4.59 GB at an effective 4.486 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), summed

Get it

4.28 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Qwen3-VL-8B-NSFW-Caption-V4.5-GGUF:IQ4_XS

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

Hugging Face CLI

hf download mradermacher/Qwen3-VL-8B-NSFW-Caption-V4.5-GGUF Qwen3-VL-8B-NSFW-Caption-V4.5.IQ4_XS.gguf

Direct download

Qwen3-VL-8B-NSFW-Caption-V4.5.IQ4_XS.gguf

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

4.28 GiB

4.59 GB

Effective bpw

4.486

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata