Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B F16

This file is exactly 8,185,077,184 bytes — 7.62 GiB / 8.19 GB at an effective 16.013 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

7.62 GiB · 1 file
llama.cpp
llama-cli -hf DavidAU/Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-gguf:F16

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

Hugging Face CLI
hf download DavidAU/Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-gguf Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-D_AU-F16.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
7.62 GiB
8.19 GB
Effective bpw
16.013
from real bytes ÷ params
Tensors
Header
GGUF metadata
Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B F16 — exact size and VRAM — ossmodeldb