deepseek-r1-14b · ValueFX9507

deepseek-r1-14b IQ4_NL

This file is exactly 17,204,533,376 bytes — 16.02 GiB / 17.20 GB at an effective 9.319 bits per weight. The nominal rate for IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

16.02 GiB · 2 files
llama.cpp
llama-cli -hf ValueFX9507/Tifa-Deepsex-14b-CoT-GGUF-Q4:IQ4_NL

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

Hugging Face CLI
hf download ValueFX9507/Tifa-Deepsex-14b-CoT-GGUF-Q4 --include "Tifa-Deepsex-14b-CoT-Chat-IQ4_NL.gguf"

This quantization is split across 2 files totalling 16.02 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
16.02 GiB
17.20 GB
Effective bpw
9.319
from real bytes ÷ params
Tensors
Header
GGUF metadata
deepseek-r1-14b IQ4_NL — exact size and VRAM — ossmodeldb