Skip to content

Model Library

MetaReleased July 18, 2023

Llama 2 Chat 13B

Meta · Released July 18, 2023

Intelligence score

3

At a glance

Intelligence
3
Speed
—
Latency
—
Input price
Not published
Output price
Not published
Context window
2tokens
Parameters
13billions

Summary

Comparison summary

Llama 2 Chat 13B scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).

Specifications

Technical specifications

Model nameLlama 2 Chat 13B
ProviderMeta
Release dateJuly 18, 2023
Intelligence score3
Speed—
Latency (TTFT)—
Input priceNot published
Output priceNot published
Context window2 tokens
Parameters13B
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsYes
LicenseLlama 2 Community License Agreement
API availability—
SourceModel Intelligence legacy profile: llama-2-chat-13b

FAQ · 16

Frequently asked questions

Llama 2 Chat 13B was released on July 18, 2023.

Llama 2 Chat 13B was created by Meta.

Llama 2 Chat 13B scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).

No, Llama 2 Chat 13B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Llama 2 Chat 13B supports text only input.

Llama 2 Chat 13B supports text only output.

No, Llama 2 Chat 13B does not support image input. It can only process text.

No, Llama 2 Chat 13B is not multimodal. It only supports text only input.

Llama 2 Chat 13B has a context window of 4.1k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Llama 2 Chat 13B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Llama 2 Chat 13B has 13 billion parameters.

Llama 2 Chat 13B is released under the Llama 2 Community License Agreement license. This license allows commercial use.

Llama 2 Chat 13B achieves a score of 3 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Llama 2 Chat 13B has a knowledge cutoff of July 2023. The model's training data includes information up to this date.

Llama 2 Chat 13B is an open weights model that can be self-hosted.

Llama 2 Chat 13B is an open weights model that can be downloaded and self-hosted.