Nemotron-3 8BOpen Weight
Released
Nemotron-3 8B is an AI model released by NVIDIA on Wednesday, Nov 15 2023, 239 days after NeMo GPT (8B/43B). It is an open-weight model — the trained weights are available to download and run. It is a 8B parameterThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. model with a 4k token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover HellaSwag, WinoGrande, and MMLU.
Get NVIDIA releases and AI news.
Every other Monday
Benchmarks
Compare Nemotron-3 8B with
Suggested comparisons
Nemotron-3 8BvsNemotron 3.5 Bolt E4B 4GBNemotron-3 8BvsGPT-6.2 AstraNemotron-3 8BvsClaude Fable 5.2Nemotron-3 8BvsGemini 4 NeonNemotron-3 8BvsMuse EmberNemotron-3 8BvsGrok 4.7Nemotron-3 8BvsDeepSeek-V4.1-Flash-1017Nemotron-3 8BvsMistral Large 4Nemotron-3 8BvsKimi K3.1 ProNemotron-3 8BvsGLM-5.3-FlashNemotron-3 8BvsQwen4-MaxAbout
NVIDIA introduced Nemotron-3 8B on November 15, 2023 as a family of text models for enterprise chat and question answering. The launch included a foundation checkpoint, supervised chat weights, two chat variants with different alignment methods, and a question-answering model.
NVIDIA made the family available through Hugging Face, its NGC catalogue and Azure. Its 8B Base checkpoint scored 54.4% on five-shot MMLU in NVIDIA’s launch evaluation. This was the 2023 Nemotron-3 line, which preceded Nemotron-4.
Frequently asked questions
Nemotron-3 8B was released by NVIDIA on Wednesday, Nov 15 2023.