MODEL LINEAGE
中文
Model index
Meta·Llama

Llama 3.3 70B

Brought near-Llama-3.1-405B instruction quality to a much smaller 70B model.

LegacyLanguageReasoningOpen weights
MODEL NUMBER150
First public date
2024-12-06
Organization
Meta
Family
Llama
01

Specifications

Only published specifications are shown.

Total parameters
70B
Architecture
Dense
Context
128,000 tokens
Input modalities
Text
Output modalities
Text
Open weights
Yes
License
Llama 3.3 Community License
Status
Legacy
02

Overview

Release dates

— Llama 3.3 70B launched. ↗

03

Specifications alongside predecessor

Compared with Llama 3.1 405B ↗

PreviousLlama 3.1 405B405B · 128K ctx
CurrentLlama 3.3 70B70B · 128K ctx
04

Architecture & capabilities

Model capabilities

MultilingualReasoning

Unclassified tags

Efficiency
05

Release history

06

Related models

Select a card to view the related model.

PredecessorLlama 3.1 405BView details →SuccessorLlama 4 ScoutView details →
07

Sources

01
The future of AI is built with LlamaMeta · Published 2024-12-19
Official · Verified
Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.