Downloads · 30 days
20
7% of all-time downloads
Llama-3.1-70B-Instruct-W4A16KV16-asym-GS-32
FabioTrindade/Llama-3.1-70B-Instruct-W4A16KV16-asym-GS-32
Llama-3.1-70B-Instruct-W4A16KV16-asym-GS-32 is a machine learning model from FabioTrindade. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.1.
This model is a quantized version of meta-llama/Llama-3.1-70B-Instruct.
All-time downloads
306
Public
Parameters
74.8B
87.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors87.6 GB · 100%
Parameter types
How the weights are stored.
I3270.6B · 94%
Base models
Model card
From the Hugging Face model README
FabioTrindade/Llama-3.1-70B-Instruct-W4A16KV16-asym-GS-32
License and Llama Use Statement
This model is a quantized version of meta-llama/Llama-3.1-70B-Instruct.
Built with Llama.
This repository provides quantized weights for research and deployment evaluation. The model is subject to the Llama 3.1 Community License and Meta's Acceptable Use Policy. Users must comply with the license terms of the original Llama 3.1 model, including applicable use restrictions, attribution requirements, and acceptable-use requirements.
Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
This repository is not affiliated with, endorsed by, or sponsored by Meta.
- Type
- llama
- License
- llama3.1
- Created
- Mar 28, 2026
- Updated
- Jul 3, 2026