Gemini-3-Pro-Qwen3.5-35B-A3B I1-Q6_K

This file is exactly 28,514,153,280 bytes — 26.56 GiB / 28.51 GB at an effective 6.581 bits per weight. The nominal rate for I1-Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

26.56 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Gemini-3-Pro-Qwen3.5-35B-A3B-i1-GGUF:I1-Q6_K

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

Hugging Face CLI
hf download mradermacher/Gemini-3-Pro-Qwen3.5-35B-A3B-i1-GGUF Gemini-3-Pro-Qwen3.5-35B-A3B.i1-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
26.56 GiB
28.51 GB
Effective bpw
6.581
from real bytes ÷ params
Tensors
Header
GGUF metadata
Gemini-3-Pro-Qwen3.5-35B-A3B I1-Q6_K — exact size and VRAM — ossmodeldb