Qwen3-VL-30B-A3B-Thinking-abliterated-v1 Q3_K_L

This file is exactly 15,900,671,744 bytes — 14.81 GiB / 15.90 GB at an effective 4.094 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

14.81 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3-VL-30B-A3B-Thinking-abliterated-v1-GGUF:Q3_K_L

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

Hugging Face CLI
hf download mradermacher/Qwen3-VL-30B-A3B-Thinking-abliterated-v1-GGUF Qwen3-VL-30B-A3B-Thinking-abliterated-v1.Q3_K_L.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
14.81 GiB
15.90 GB
Effective bpw
4.094
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen3-VL-30B-A3B-Thinking-abliterated-v1 Q3_K_L — exact size and VRAM — ossmodeldb