LLM
Nemotron-4 340B
Nemotron-4 340B is an NVIDIA open model family (Base, Instruct, Reward) built to generate synthetic training data for other LLMs.
Levelmodel
ClassLLM
Parameters340B
Context4,096
Released14 Jun 2024
Opennessopen weights permissive
Runs onmulti-GPU node
Statusnot in the notes
Benchmark Results
vendor-reported
GSM8Kmath
Instruct model; 0-shotvendor-reported
92.3
050100
Score in %. Higher is better.
HumanEvalcoding
Instruct model; 0-shotvendor-reported
73.2
050100
Score in %. Higher is better.
IFEvalknowledge and reasoning
Instruct model; prompt-strict accuracyvendor-reported
79.9
050100
Score in %. Higher is better.
MMLUknowledge and reasoning
Instruct model; 0-shotvendor-reported
78.7
050100
Score in %. Higher is better.
MT-Benchknowledge and reasoning
Instruct model; judged by GPT-4-0125-Previewvendor-reported
8.22
04.59
Score in score. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
instruct of
Nemotron-4-340B-Base is the parent (instruct of)high confidencemodel cardWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Decoder-only transformer with GQA and RoPE; family has Base, Instruct and Reward models
- Total parameters
- 340B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 4,096 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- NVIDIA Open Model License sources
- Access routes
- open weights download, API
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- multi-GPU node
- Footprint
- BF16 inference: 8x H200 (one node), 16x H100 or 16x A100 80GB (two nodes)
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Instruct model intended for English; base pre-trained on English text, 50+ natural languages and 40+ coding languages
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperNVIDIAbig tech, USA
NVIDIAbig tech, USAModelNemotron-4 340BNVIDIA, LLM
Nemotron-4 340BNVIDIA, LLMUse CasesClinical LLM (Open Weights)HealthcareProcess Optimisation and Advanced Process ControlIndustrialTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025
Conch CementIn production, 23 Jun 2025
PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025Conch CementIn production, 23 Jun 2025PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.Organisations 1
Sources
- blogs.nvidia.com/blog/nemotron-4-synthetic-data-generation-llm... https://blogs.nvidia.com/blog/nemotron-4-synthetic-data-generation-llm-training/
- huggingface.co/nvidia/Nemotron-4-340B-Instruct https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
- huggingface.co/api/models/nvidia/Nemotron-4-340B-Instruct https://huggingface.co/api/models/nvidia/Nemotron-4-340B-Instruct
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Nemotron-4 340B", https://aurion.semai.id/models/nvidia-nemotron-4-340b/, records of October 2026.