Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF · PiehSoft

Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF Q5_K_M

This file is exactly 28,646,588,384 bytes — 26.68 GiB / 28.65 GB at an effective 5.865 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

26.68 GiB · 1 file
llama.cpp
llama-cli -hf PiehSoft/Qwen3.6-40B-Deckard-MTP:Q5_K_M

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

Hugging Face CLI
hf download PiehSoft/Qwen3.6-40B-Deckard-MTP Qwen3.6-40B-Deckard-MTP-Q5_K_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.

Repository →
Size
26.68 GiB
28.65 GB
Effective bpw
5.865
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF Q5_K_M — exact size and VRAM — ossmodeldb