Leanstral-1.5-119B-A6B NVFP4

This file is exactly 67,135,119,264 bytes — 62.52 GiB / 67.14 GB at an effective 4.514 bits per weight. The nominal rate for NVFP4 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

62.52 GiB · 1 file
llama.cpp
llama-cli -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

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

Hugging Face CLI
hf download Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 Leanstral-1.5-119B-A6B-NVFP4.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
62.52 GiB
67.14 GB
Effective bpw
4.514
from real bytes ÷ params
Tensors
Header
GGUF metadata