Qwen3.5-13B-Strict-Instruct · mradermacher

Qwen3.5-13B-Strict-Instruct I1-Q4_K_M

This file is exactly 7,732,387,360 bytes — 7.20 GiB / 7.73 GB at an effective 4.983 bits per weight. The nominal rate for I1-Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

7.20 GiB · 1 file

llama.cpp

llama-cli -hf mradermacher/Qwen3.5-13B-Strict-Instruct-i1-GGUF:I1-Q4_K_M

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

Hugging Face CLI

hf download mradermacher/Qwen3.5-13B-Strict-Instruct-i1-GGUF Qwen3.5-13B-Strict-Instruct.i1-Q4_K_M.gguf

Direct download

Qwen3.5-13B-Strict-Instruct.i1-Q4_K_M.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

7.20 GiB

7.73 GB

Effective bpw

4.983

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata