Llama-3.3-70B-Instruct-abliterated-finetuned · DevQuasar-5
Llama-3.3-70B-Instruct-abliterated-finetuned Q6_K
This file is exactly 57,888,153,216 bytes — 53.91 GiB / 57.89 GB at an effective 6.564 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 5 file(s), summed
Get it
53.91 GiB · 5 files
llama.cpp
llama-cli -hf DevQuasar-5/huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download DevQuasar-5/huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned-GGUF --include "huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-*-of-*.gguf"
This quantization is split across 5 files totalling 53.91 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 5 required
- huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-00001-of-00005.gguf
- huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-00002-of-00005.gguf
- huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-00003-of-00005.gguf
- huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-00004-of-00005.gguf
- huihui-ai.Llama-3.3-70B-Instruct-abliterated-finetuned.Q6_K-00005-of-00005.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
53.91 GiB
57.89 GB
Effective bpw
6.564
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata