Downloads · 30 days
12
40% of all-time downloads
Llama-3.1-70B-Instruct-bnb-4bit
lierseleow/Llama-3.1-70B-Instruct-bnb-4bit
Llama-3.1-70B-Instruct-bnb-4bit is a machine learning model from lierseleow. 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 repository contains quantized weights for meta-llama/Llama-3.1-70B-Instruct.
All-time downloads
30
Public
Parameters
70.6B
39.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors39.5 GB · 100%
Parameter types
How the weights are stored.
U868.5B · 97%
Base models
Model card
From the Hugging Face model README
lierseleow/Llama-3.1-70B-Instruct-bnb-4bit (Quantized)
This repository contains quantized weights for meta-llama/Llama-3.1-70B-Instruct.
License & Attribution
Built with Meta Llama 3.1.
This model is a derivative work of Meta's Llama 3.1 and is governed by the Llama 3.1 Community License Agreement.
- Official License: Llama 3.1 Community License
- Acceptable Use Policy: Meta Llama Acceptable Use Policy
By downloading, copying, or using these quantized weights, you agree to compliance with the terms, conditions, and restrictions outlined in the official license.
Quantization Details
- Quantization Method: bitsandbytes
- Bits/Precision: 4bit
- Base Model: meta-llama/Llama-3.1-70B-Instruct
Dependencies Details
- transformers version: 5.14.1
- bitsandbytes version: 0.50.0
- Type
- llama
- License
- llama3.1
- Created
- Aug 21, 2026
- Updated
- Aug 23, 2026