Nvidia LLM Models

There are 90 Open Source LLM Models by Nvidia

N V Embed v2

Feature Extraction

Eagle2 9 B

Image Text To Text

Cosmos 1.0 Diffusion 7 B Text2 World

Llama 3.1 Nemotron 70 B Instruct H F

Text Generation

Eagle2 1 B

Image Text To Text

stt_be_fastconformer_hybrid_large_pc

Automatic Speech Recognition

diar_sortformer_4spk v1

Audio Classification

Llama 3.1 8 B Medusa F P8

Nemo Guard Jailbreak Detect

X Mobility

speakerverification_en_titanet_large

N V Embed v1

Nemotron 4 340 B Instruct

Nemotron Mini 4 B Instruct

Llama 3_1 Nemotron 51 B Instruct

Text Generation

Llama 3.1 Nemotron 70 B Instruct

Cosmos 1.0 Tokenizer C V8x8x8

Cosmos 1.0 Diffusion 14 B Video2 World

Eagle2 2 B

Image Text To Text

llama 3.1 nemoguard 8b content safety

Text Classification

mit b0

Image Classification

segformer b0 finetuned ade 512 512

Image Segmentation

segformer b0 finetuned cityscapes 1024 1024

Image Segmentation

segformer b1 finetuned cityscapes 1024 1024

Image Segmentation

stt_zh_conformer_transducer_large

Automatic Speech Recognition

stt_be_conformer_ctc_large

Automatic Speech Recognition

stt_be_conformer_transducer_large

Automatic Speech Recognition

Ace Instruct 72 B

Text Generation

Cosmos 1.0 Autoregressive 4 B

Ace Instruct 1.5 B

Text Generation

Cosmos 1.0 Diffusion 7 B Video2 World

Cosmos 1.0 Diffusion 14 B Text2 World

Ace Math 7 B Instruct

Text Generation

Cosmos 1.0 Autoregressive 5 B Video2 World

Ace Math 72 B Instruct

Text Generation

Ace Math 72 B R M

Text Generation

canary 1b

Automatic Speech Recognition

Ace Math 7 B R M

Text Generation

parakeet rnnt 1.1b

Automatic Speech Recognition

Ace Instruct 7 B

Text Generation

Cosmos 1.0 Autoregressive 13 B Video2 World

Cosmos 1.0 Autoregressive 12 B

Cosmos 1.0 Guardrail

Ace Math 1.5 B Instruct

Text Generation

llama 3.1 nemoguard 8b topic control

Text Classification

domain classifier

C R A D I Ov2 G

Feature Extraction

segformer b1 finetuned ade 512 512

Image Segmentation

Faster Vi T

N V L M D 72 B mcore

Image Text To Text

Cosmos 1.0 Tokenizer D V8x16x16

bigvgan_v2_44khz_128band_512x

Audio To Audio

N V L M D 72 B

Image Text To Text

Hymba 1.5 B Instruct

Text Generation

Cosmos 0.1 Tokenizer C V8x8x8

nemotron 3 8b base 4k

Text Generation

Mistral Ne Mo Minitron 8 B Base

Text Generation

Llama 3.1 8 B Instruct F P8

Hymba 1.5 B Base

Text Generation

Cosmos 0.1 Tokenizer D V4x8x8

ssl_en_nest_large_v1.0

Cosmos 1.0 Prompt Upsampler 12 B Text2 World

Cosmos 1.0 Diffusion 7 B Decoder D V8x16x16 To C V8x8x8

megatron bert uncased 345m

stt_en_conformer_transducer_xlarge

Automatic Speech Recognition

tts_en_fastpitch

Text To Speech

stt_ru_conformer_transducer_large

Automatic Speech Recognition

stt_eo_conformer_transducer_large

Automatic Speech Recognition

Cosmos 0.1 Tokenizer C I8x8

Cosmos 0.1 Tokenizer C I16x16

quality classifier deberta

Mistral Ne Mo Minitron 8 B Instruct

Text Generation

M M Embed

bigvgan_v2_22khz_80band_256x

Audio To Audio

ssl_en_nest_xlarge_v1.0

parakeet tdt_ctc 110m

Automatic Speech Recognition

Meta Llama 3.2 3 B Instruct O N N X I N T4

multilingual domain classifier

content type classifier deberta

prompt task and complexity classifier

megatron bert cased 345m

segformer b2 finetuned ade 512 512

Image Segmentation

segformer b5 finetuned ade 640 640

Image Segmentation

segformer b5 finetuned cityscapes 1024 1024

Image Segmentation

tts_hifigan

Text To Speech

stt_uk_citrinet_1024_gamma_0_25

Automatic Speech Recognition

nemo megatron gpt 1.3 B

Text2text Generation

Nemotron 4 Mini Hindi 4 B Instruct

Mamba Vision S 1 K

Image Feature Extraction

stt_en_fastconformer_tdt_large

Automatic Speech Recognition