LLM Reference

Model Families

414 model families across leading AI researchers

Llama 3

Llama 3

AI at Meta

Llama 2

Llama 2

AI at Meta

Mixtral

Mixtral

MistralAI

Gemma

Gemma

Google DeepMind

Llama 3.1

Llama 3.1

AI at Meta

Qwen2

Qwen2

Alibaba

Grok

Grok

xAI

Qwen1.5

Qwen1.5

Alibaba

Gemma 2

Gemma 2

Google DeepMind

Gemini 2.0

Gemini 2.0

Google DeepMind

Code Llama

Code Llama

AI at Meta

GPT-4o

GPT-4o

OpenAI

DBRX

DBRX

Databricks Mosaic

Llama 3.2

Llama 3.2

AI at Meta

Command R

Command R

Cohere For AI

Sonar

Sonar

Perplexity Labs

Command

Command

Cohere For AI

Solar Mini

Solar Mini

Upstage

Yi

Yi

AI

CodeGemma

CodeGemma

Google DeepMind

Arctic

Arctic

Snowflake

DeepSeek Coder V2

DeepSeek Coder V2

DeepSeek

DeepSeek

DeepSeek

DeepSeek

DeepSeek Math

DeepSeek Math

DeepSeek

StableLM

StableLM

Stability AI

DeepSeek V2

DeepSeek V2

DeepSeek

StableLM 2

StableLM 2

Stability AI

Stable Code

Stable Code

Stability AI

Yi-1.5 (2024/05)

Yi-1.5 (2024/05)

AI

o1

o1

OpenAI

DeepSeek VL

DeepSeek VL

DeepSeek

Palmyra X

Palmyra X

Writer

PaliGemma

PaliGemma

Google DeepMind

RakutenAI

RakutenAI

Rakuten

Jamba 1.5

Jamba 1.5

AI21 Labs

RecurrentGemma

RecurrentGemma

Google DeepMind

Fuyu

Fuyu

Adept AI

Smaug

Smaug

Abacus.AI

Replit Code

Replit Code

Replit

CodeQwen1.5

CodeQwen1.5

Alibaba

abab

abab

MiniMax

DeepSeek MoE

DeepSeek MoE

DeepSeek

Phi-3.5

Phi-3.5

Microsoft Research

Smaug 2

Smaug 2

Abacus.AI

Solar 0

Solar 0

Upstage

Mistral 7B

MistralAI

Qwen2.5

Qwen2.5

Alibaba

DeepSeek V3

DeepSeek V3

DeepSeek

Gemma 3

Gemma 3

Google DeepMind

Mistral Small

Phi-3

Phi-3

Microsoft Research

DeepSeek R1

DeepSeek R1

DeepSeek

Llama 4

AI at Meta

Kimi

Kimi

Moonshot AI

Phi-4

Phi-4

Microsoft Research

Qwen3

GLM-4

GLM-4

Tsinghua Knowledge Engineering Group (THUDM)

GPT-OSS

GPT-OSS

OpenAI

Nemotron-3

Nemotron-3

NVIDIA AI

NeMo

NeMo

MistralAI

Nvidia

Dolphin

Dolphin

Cognitive Computations

Hermes 2

Hermes 2

Nous Research

Falcon

Falcon

Technology Innovation Institute (TII)

Minimax

Yi (2023/11)

Yi (2023/11)

AI

DeepSeek Coder

DeepSeek Coder

DeepSeek

Qwen 3

Sarvam

Mistral Medium

Llama Guard

Llama Guard

AI at Meta

OpenChat 3

OpenChat 3

Alignment Lab AI

GPT-3.5

GPT-3.5

OpenAI

Mistralai

Leanstral

MistralAI

Nemotron-Cascade

NVIDIA AI

Granite 4

Qwen 3.5

Phi-2

Phi-2

Microsoft Research

WizardLM-2

WizardLM-2

Dreamgen

Qwen2.5 Coder

Qwen2.5 Coder

Alibaba

Mixtral 8x7B

MistralAI

Zephyr

Zephyr

Hugging Face H4

Transcribe

Cohere For AI

o3

o3

OpenAI

DeepSeek V4

DeepSeek

Nemotron Nano 2

NVIDIA AI

Llama 3.3

AI at Meta

Amazon Titan Text

Amazon Web Services (AWS) AI

Mytho

Mytho

Gryphe Padar

StarCoder 2

StarCoder 2

ServiceNow Research

Ibm Granite

Claude 3.5

Anthropic

Hermes

Hermes

Nous Research

Code Llama

AI at Meta

OpenHermes 2

OpenHermes 2

Teknium

Thedrummer

Amazon Nova

Amazon Web Services (AWS) AI

Vicuna

Vicuna

LMSYS Org

Marin

Marin

Command

Cohere For AI

Qwen 3 Coder

Qwen 3 Coder

WizardLM

WizardLM

WizardLM Team

OLMo

OLMo

Allen Institute for Artificial Intelligence (AI2)

Granite 3

Granite 3

IBM Research

OpenOrca

OpenOrca

Alignment Lab AI

Granite Code

Granite Code

IBM Research

LLaVA 1.6

LLaVA 1.6

Haotian Liu

Phind CodeLlama

Phind CodeLlama

Phind

Kimi K2

Kimi K2

Moonshot AI

WizardCoder

WizardCoder

WizardLM Team

Gemini 2.5

Meta Llama

Doubao

Doubao

ByteDance

Aya

Aya

Cohere For AI

Prompt Guard

Prompt Guard

AI at Meta

Qwen

Alibaba

Pythia

Pythia

EleutherAI

FLAN-T5

FLAN-T5

Google DeepMind

FireMoE

Fireworks AI

Llama 3.3

AI at Meta

Jet-Nemotron

NVIDIA AI

Sao10K

Gemini 2.0

Capybara

Capybara

Nous Research

Baichuan 2

Baichuan 2

Baichuan Intelligent Technology

Jurassic-2

Jurassic-2

AI21 Labs

Orca 2

Orca 2

Microsoft Research

Nemotron-4

Nemotron-4

NVIDIA AI

Swallow

Tokyo Institute of Technology

Pixtral

Pixtral

MistralAI

ChatGLM3

ChatGLM3

Tsinghua Knowledge Engineering Group (THUDM)

Qwen VL

Alibaba

ELYZA Japanese Llama 2

ELYZA Japanese Llama 2

ELYZA

Dolly 2.0

Dolly 2.0

Databricks Mosaic

GPT-JT

GPT-JT

Together.ai

Starling

Starling

Nexusflow

NVIDIA Llama 3 ChatQA

NVIDIA Llama 3 ChatQA

NVIDIA AI

Codestral

Codestral

MistralAI

SQLCoder

SQLCoder

Defog.ai

Jamba

Jamba

AI21 Labs

Chronos Hermes

Chronos Hermes

Austism

Granite

Granite

IBM Research

Jais

Jais

Core42

Japanese StableLM

Japanese StableLM

Stability AI

MPT

MPT

Databricks Mosaic

Stockmark

Stockmark

Re:MythoMax

Re:MythoMax

Undi95

Toppy

Toppy

Undi95

Snorkel

Snorkel

Snorkel AI

Cogito

Cogito

Titan

Titan

Amazon Web Services (AWS) AI

MT0

MT0

BigScience

Mamba

Mamba

State Spaces

Nova

Nova

Amazon Web Services (AWS) AI

MiniMax M2

MiniMax M2

MiniMax

Gradient Llama 3

Gradient Llama 3

Gradient

Rerank

Rerank

Cohere For AI

NSQL

NSQL

NumbersStation

LLaVA

LLaVA

Haotian Liu

Italia

iGenius

GLM-Z1

KAT

KAT

TenyxChat

TenyxChat

Tenyx

NeVA

NeVA

NVIDIA AI

Platypus2

Platypus2

garage-bAInd

Aquila 2

Aquila 2

Beijing Academy of Artificial Intelligence (BAAI)

airoboros

airoboros

Jon Durbin

Ministral

MistralAI

Colosseum

iGenius

MiniMax M1

MiniMax M1

MiniMax

Yi VL

Yi VL

AI

Qwen2.5 Math

Qwen2.5 Math

Alibaba

SEA-LION

SEA-LION

AI Singapore

StableLM 2

Stability AI

SeaLLM 2

SeaLLM 2

Alibaba

Nous Llama 3

Nous Llama 3

Nous Research

Tulu

Tulu

Allen Institute for Artificial Intelligence (AI2)

LLaVA 1.5

LLaVA 1.5

Haotian Liu

Firefunction

Firefunction

Fireworks AI

DeciLM

DeciLM

Deci AI

Striped Hyena

Striped Hyena

Together.ai

Breeze

Breeze

MediaTek-Research

NexusRaven

NexusRaven

Nexusflow

Llemma

Llemma

EleutherAI

Phi-1

Phi-1

Microsoft Research

DeciCoder

DeciCoder

Deci AI

InternLM

InternLM

Intern-AI

StarCoder

StarCoder

ServiceNow Research

Alpaca

Alpaca

Stanford ArtificiaI Intelligence Laboratory (SAIL)

Cerebras GPT

Cerebras GPT

Cerebras

Bielik

SpeakLeash

Kling

DeepSeek Prover

DeepSeek Prover

DeepSeek

FARE

FARE

Fireworks AI

Qwen 2 VL

Alibaba

Qwen 3 VL

Qwen 3 VL

Teuken

OpenGPT-X

NVLM

NVLM

NVIDIA AI

Dracarys

Abacus AI

Merlinite

Merlinite

IBM Research

SaulLM

SaulLM

Equall

StarCoder2

BigScience

Zamba 2

Zamba 2

Zyphra

InternLM2-Math

InternLM2-Math

Intern-AI

FireLLaVA

FireLLaVA

Fireworks AI

Fugaku-LLM

Fugaku-LLM

Fujitsu

DePlot

DePlot

Google DeepMind

ALLaM

ALLaM

Saudi Data and Artificial Intelligence Authority

Llama 2 (Korean)

Llama 2 (Korean)

Minds And Company

Together Llama 2

Together Llama 2

Together.ai

Open-Assistant

Open-Assistant

OpenAssistant

Camel

Camel

Writer

Kosmos-2

Kosmos-2

Microsoft Research

LLaMA

AI at Meta

FLAN-UL2

FLAN-UL2

Google DeepMind

Moonshotai

Mamba 2

Mamba 2

State Spaces

MetaMath

MetaMath

MetaMath

Palmyra

Palmyra

Writer

Embed

Cohere For AI

Rerank

Cohere For AI

MiniCPM

OpenBMB

Fire Qwen

Fireworks AI

Doubao 1.5

Doubao 1.5

ByteDance

Yi Coder

Yi Coder

AI

Llama 3.2

AI at Meta

OpenELM

OpenELM

Apple Machine Learning Research

Pangu

Pangu

Huawei Noah's Ark Lab

XuanYuan

XuanYuan

Du Xiaoman Data Intelligence

WizardMath

WizardMath

WizardLM Team

Aquila

Aquila

Beijing Academy of Artificial Intelligence (BAAI)

Chronos Llama 2

Chronos Llama 2

Elinas

GPT-4o Realtime

GPT-4o Realtime

OpenAI

SmolLM

SmolLM

Hugging Face TB

Hermes 3

Hermes 3

Nous Research

Samba-1

Samba-1

SambaNova Systems

Moonshot

Moonshot

Moonshot AI

Nous Llama 3.1

Nous Llama 3.1

Nous Research

Cambrian

Cambrian

New York University

InternLM-XComposer2

InternLM-XComposer2

Intern-AI

InternLM2

InternLM2

Intern-AI

OpenChat 2

OpenChat 2

Alignment Lab AI

NuExtract

NuExtract

NuMind

OpenChat

OpenChat

Alignment Lab AI

Palmyra Med

Palmyra Med

Writer

Nous Llama 2

Nous Llama 2

Nous Research

Baichuan

Baichuan

Baichuan Intelligent Technology

GigaChat

GigaChat

Gigachat (Sberbank)

Openrouter

CogVLM2

ChatGLM-4

GPT-4o Audio

GPT-4o Audio

OpenAI

Doubao Vision

Doubao Vision

ByteDance

LTX

f1

f1

Fireworks AI

Vidu

Cerebras LLaVA

Cerebras LLaVA

Cerebras

DCLM

DCLM

Apple Machine Learning Research

NuExtract 1.5

NuExtract 1.5

NuMind

Chameleon

Chameleon

AI at Meta

Florence 2

Florence 2

Microsoft Research

EON

EON

LinkedIn

SeaLLM

SeaLLM

Alibaba

Phind

Phind

Phind

GOAT

GOAT

GOAT.AI

Japanese StableLM 2

Japanese StableLM 2

Stability AI

InternLM-XComposer

InternLM-XComposer

Intern-AI

RedPajama

RedPajama

Together.ai

OpenHermes

OpenHermes

Teknium

YandexGPT

YandexGPT

Yandex

StarChat

StarChat

Hugging Face H4

FireGemini

Fireworks AI

Fire Llama 3

Fireworks AI

Qwen

Qwen

Alibaba

Zamba

Zamba

Zyphra

LearnLM

LearnLM

Google DeepMind

Stable LM 2.5

Fireworks Dev

Fireworks AI

Z-Image

Stable Virtual Assistant

IBM Granite Code

LingoWhale

LingoWhale

DeepLang AI

Imbue

Imbue

Imbue

Fireworks Chat

Fireworks AI

Fireworks Functions

Fireworks AI

Athene

Athene

Nexusflow

Kosmos-2.5

Kosmos-2.5

Microsoft Research

Mathstral

Mathstral

MistralAI

StarChat2

StarChat2

Hugging Face H4

Babble

Babble

Supermaven

Apple Intelligence On-Device

Apple Intelligence On-Device

Apple Machine Learning Research

Apple Intelligence Server

Apple Intelligence Server

Apple Machine Learning Research

Falcon2

Falcon2

Technology Innovation Institute (TII)

360Zhinao

Qihoo 360

Inflection-2.5

Inflection-2.5

Inflection

XuanYuan 2

XuanYuan 2

Du Xiaoman Data Intelligence

EvoLLM

Sakana AI

Palmyra Vision

Palmyra Vision

Writer

Starling Alpha

Starling Alpha

Berkeley Artificial Intelligence Research (BAIR)

Palmyra Finance

Palmyra Finance

Writer

Baichuan 3

Baichuan 3

Baichuan Intelligent Technology

GLM

GLM

Tsinghua Knowledge Engineering Group (THUDM)

Chronos Mistral

Chronos Mistral

Elinas

Inflection-2

Inflection-2

Inflection

BlueLM

BlueLM

Vivo AI Lab

PLaMo

Preferred Networks

Persimmon

Persimmon

Adept AI

ELYZA Japanese CodeLlama

ELYZA Japanese CodeLlama

ELYZA

Platypus

Platypus

garage-bAInd

Inflection-1

Inflection-1

Inflection

Orca

Orca

Microsoft Research

GPT4All

Nomic AI

Open-CALM

CyberAgent

Dolly

Dolly

Databricks Mosaic

Chronos Llama 1

Chronos Llama 1

Elinas

KoGPT

Kakao

Alibaba

Alpindale

Anthracite Org

Gemini 2.0

GPT-4.1

OpenAI

o4-mini

OpenAI

Qwen 2.5

Alibaba

Switchpoint

Z Ai

Ai21

Aion Labs

Alfredpros

Allenai

Amazon

Arcee Ai

Athene V2

Athene V2

Nexusflow

Aya

Cohere For AI

Baidu

BloombergGPT

BloombergGPT

Bloomberg

Bytedance

Bytedance Seed

CodeGen

CodeGen

Salesforce AI Research

CodeTulu 2

CodeTulu 2

Allen Institute for Artificial Intelligence (AI2)

Cognitivecomputations

Cohere

Deepcogito

ELYZA Japanese Llama 3

ELYZA Japanese Llama 3

ELYZA

Essentialai

Fire LLaVA

Fireworks AI

GatorTron

GatorTron

UFNLP

GPT-Neo

GPT-Neo

EleutherAI

GPT-NeoX

GPT-NeoX

EleutherAI

Granite Geospatial

Granite Geospatial

IBM Research

Granite Guardian

Granite Guardian

IBM Research

Granite Time Series

Granite Time Series

IBM Research

Hunyuan

Hunyuan

Tencent AI Lab

KAI-GPT

KAI-GPT

Kasisto

Koala

Koala

Berkeley Artificial Intelligence Research (BAIR)

Kosmos-1

Kosmos-1

Microsoft Research

Kwaipilot

Liquid

LLaVaOLMoBitnet

LLaVaOLMoBitnet

Intel Labs

LLM Compiler

LLM Compiler

AI at Meta

MagicLM

MagicLM

Honor

Mancer

Meituan

MoMo

MoMo

Moreh

Morph

Moshi

Moshi

Kyutai

Nex Agi

Nousresearch

o4

OpenAI

Openai

Perplexity

Phi

Prime Intellect

QwQ

Alibaba

Relace

Solar Pro

Solar Pro

Upstage

SparkDesk

SparkDesk

iFLYTEK Developer

SparkDesk 2.0

SparkDesk 2.0

iFLYTEK Developer

SparkDesk 3.0

SparkDesk 3.0

iFLYTEK Developer

SparkDesk 3.5

SparkDesk 3.5

iFLYTEK Developer

SQL-GPT

SQL-GPT

Kinetica

Stepfun

Tencent

Tianshu

Tianshu

Intellifusion (Shenzhen Yuntian Lifei)

Tngtech

Tulu 3

Tulu 3

Allen Institute for Artificial Intelligence (AI2)

Tulu V2

Tulu V2

Allen Institute for Artificial Intelligence (AI2)

Tulu v2.5

Tulu v2.5

Allen Institute for Artificial Intelligence (AI2)

Upstage

Writer

X Ai

xDAN L1

xDAN L1

xDAN-AI

xDAN L2

xDAN L2

xDAN-AI

XGen

XGen

Salesforce AI Research

Xiaomi

Xinghai

Xinghai

Hisense

xLAM

xLAM

Salesforce AI Research