HunyuanVideo · calcuis

HunyuanVideo F16

This file is exactly 16,069,941,568 bytes — 14.97 GiB / 16.07 GB at an effective 10.027 bits per weight. The nominal rate for F16 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

14.97 GiB · 1 file

llama.cpp

llama-cli -hf calcuis/hyvid:F16

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

Hugging Face CLI

hf download calcuis/hyvid llava_llama3-f16.gguf

Direct download

llava_llama3-f16.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

14.97 GiB

16.07 GB

Effective bpw

10.027

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata