Qwen3-VL-32B-Instruct-abliterated-v1 · mradermacher
Qwen3-VL-32B-Instruct-abliterated-v1 I1-IQ2_M
This file is exactly 11,362,863,328 bytes — 10.58 GiB / 11.36 GB at an effective 2.725 bits per weight. The nominal rate for I1-IQ2_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
10.58 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3-VL-32B-Instruct-abliterated-v1-i1-GGUF:I1-IQ2_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Qwen3-VL-32B-Instruct-abliterated-v1-i1-GGUF Qwen3-VL-32B-Instruct-abliterated-v1.i1-IQ2_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.
Size
10.58 GiB
11.36 GB
Effective bpw
2.725
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata