HiDream-I1-Full · calcuis
HiDream-I1-Full Q3_K_M
This file is exactly 48,214,971,712 bytes — 44.90 GiB / 48.21 GB at an effective 22.549 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 5 file(s), summed
Get it
44.90 GiB · 5 files
llama.cpp
llama-cli -hf calcuis/hidream-gguf:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download calcuis/hidream-gguf --include "hidream-e1-1-q3_k_m.gguf"
This quantization is split across 5 files totalling 44.90 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 5 required
- hidream-e1-1-q3_k_m.gguf
- hidream-i1-dev-q3_k_m.gguf
- hidream-i1-fast-q3_k_m.gguf
- hidream-i1-full-fp32-q3_k_m.gguf
- hidream-i1-full-q3_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.
Size
44.90 GiB
48.21 GB
Effective bpw
22.549
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata