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

Qwen3-VL-8B-NSFW-Caption-V4.5-heretic Q3_K_L

This file is exactly 4,431,395,584 bytes — 4.13 GiB / 4.43 GB at an effective 4.328 bits per weight. The nominal rate for Q3_K_L is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

4.13 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Qwen3-VL-8B-NSFW-Caption-V4.5-heretic-GGUF:Q3_K_L

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

Hugging Face CLI

hf download mradermacher/Qwen3-VL-8B-NSFW-Caption-V4.5-heretic-GGUF Qwen3-VL-8B-NSFW-Caption-V4.5-heretic.Q3_K_L.gguf

Direct download

Qwen3-VL-8B-NSFW-Caption-V4.5-heretic.Q3_K_L.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

4.13 GiB

4.43 GB

Effective bpw

4.328

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata