NIM Serverless Inference API - a nvidia Collection

nvidia 's Collections

Optimized ONNX models for NVIDIA RTX GPUs

Cosmos Tokenizer

Llama-3.1-Nemotron-70B

Nemotron 4 340B

SteerLM

Canary

RLHF

Llama3-ChatQA-1.5

SSMs

BigVGAN

RADIO

NIM Serverless Inference API

Model Optimizer

Llama3-ChatQA-2

NeMo Curator - Classifier Models

NIM Serverless Inference API

updated Oct 14

Models in this collection are available for inference via a serverless API powered by NVIDIA NIM.

meta-llama/Llama-3.1-8B-Instruct

Text Generation • Updated Sep 25 • 6.07M • • 3.09k

Note NIM LLM deployed with H100 x 1
meta-llama/Llama-3.1-70B-Instruct

Text Generation • Updated Sep 25 • 3.43M • • 691

Note NIM LLM deployed with H100 x 4
meta-llama/Llama-3.1-405B-Instruct-FP8

Text Generation • Updated Sep 25 • 72.6k • 175

Note NIM LLM deployed with H100 x 8
meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated Sep 27 • 2.57M • • 3.63k

Note NIM LLM deployed with H100 x 1
meta-llama/Meta-Llama-3-70B-Instruct

Text Generation • Updated Sep 27 • 161k • • 1.44k

Note NIM LLM deployed with H100 x 4
mistralai/Mistral-7B-Instruct-v0.3

Text Generation • Updated Aug 21 • 555k • • 1.14k

Note NIM LLM deployed with H100 x 2
mistralai/Mixtral-8x7B-Instruct-v0.1

Text Generation • Updated Aug 19 • 487k • • 4.21k

Note NIM LLM deployed with H100 x 2
mistralai/Mixtral-8x22B-Instruct-v0.1

Text Generation • Updated Oct 3 • 144k • 690

Note NIM LLM deployed with H100 x 8