SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled I1-Q6_K

This file is exactly 22,431,000,096 bytes — 20.89 GiB / 22.43 GB at an effective 6.568 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

20.89 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled-i1-GGUF:I1-Q6_K

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

Hugging Face CLI
hf download mradermacher/SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled-i1-GGUF SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled.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
20.89 GiB
22.43 GB
Effective bpw
6.568
from real bytes ÷ params
Tensors
Header
GGUF metadata