Qwen2.5-VL-7B-NSFW-Caption-V3 IQ3_XXS

This file is exactly 3,114,513,280 bytes — 2.90 GiB / 3.11 GB at an effective 3.272 bits per weight. The nominal rate for IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.90 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-GGUF:IQ3_XXS

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

Hugging Face CLI
hf download bartowski/thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-GGUF thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-IQ3_XXS.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
2.90 GiB
3.11 GB
Effective bpw
3.272
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen2.5-VL-7B-NSFW-Caption-V3 IQ3_XXS — exact size and VRAM — ossmodeldb