Qwen3-VL-30B-A3B-Instruct-abliterated-v1 · mradermacher
Qwen3-VL-30B-A3B-Instruct-abliterated-v1 IQ4_XS
This file is exactly 16,557,094,752 bytes — 15.42 GiB / 16.56 GB at an effective 4.263 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
15.42 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF:IQ4_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF Qwen3-VL-30B-A3B-Instruct-abliterated-v1.IQ4_XS.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
15.42 GiB
16.56 GB
Effective bpw
4.263
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata