Rombos-LLM-V2.5-Qwen-14b · bartowski
Rombos-LLM-V2.5-Qwen-14b IQ2_S
This file is exactly 5,003,726,752 bytes — 4.66 GiB / 5.00 GB at an effective 2.710 bits per weight. The nominal rate for IQ2_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
4.66 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF:IQ2_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF Replete-LLM-V2.5-Qwen-14b-IQ2_S.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
4.66 GiB
5.00 GB
Effective bpw
2.710
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata