Qwen3-VL-4B-Instruct-c_abliterated-v2 · mradermacher
Qwen3-VL-4B-Instruct-c_abliterated-v2 Q6_K
This file is exactly 3,306,263,328 bytes — 3.08 GiB / 3.31 GB at an effective 5.960 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
3.08 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3-VL-4B-Instruct-c_abliterated-v2-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Qwen3-VL-4B-Instruct-c_abliterated-v2-GGUF Qwen3-VL-4B-Instruct-c_abliterated-v2.Q6_K.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
3.08 GiB
3.31 GB
Effective bpw
5.960
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata