Qwen3.6-35B-A3B-NSC-ACE-SABER · GestaltLabs

Qwen3.6-35B-A3B-NSC-ACE-SABER Q3_K_S

This file is exactly 15,182,184,224 bytes — 14.14 GiB / 15.18 GB at an effective 3.421 bits per weight. The nominal rate for Q3_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

14.14 GiB · 1 file

llama.cpp

llama-cli -hf GestaltLabs/Qwen3.6-35B-A3B-NSC-ACE-SABER-GGUF:Q3_K_S

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

Hugging Face CLI

hf download GestaltLabs/Qwen3.6-35B-A3B-NSC-ACE-SABER-GGUF Qwen3.6-35B-A3B-NSC-ACE-SABER-Q3_K_S.gguf

Direct download

Qwen3.6-35B-A3B-NSC-ACE-SABER-Q3_K_S.gguf

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.

Repository →

Size

14.14 GiB

15.18 GB

Effective bpw

3.421

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata