NVIDIA Nemotron-4 340B Specs, Benchmarks & Downloads
NVIDIA Nemotron-4 340B
NVIDIA enterprise language model
Status
active
Parameters
340.00
Context Window
4096
Modality
Text
Release Date
Jun 11, 2024
About
Explore NVIDIA Nemotron-4 340B, a text AI model developed by NVIDIA. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
NVIDIA Nemotron provides a large-scale model optimized for enterprise AI workloads.
Family
NemotronDeveloper
NVIDIAArchitecture
Mixture of ExpertsLicense
Apache 2.0Hardware Requirements
Minimum:
Use Case: Distributed inference
GPU Minimum:
GPU VRAM:
System RAM: 512GB
Storage: 1TB
Operating System: Linux
340B model requires multi GPU infrastructure
Recommended:
Use Case: Server inference
GPU Minimum: 8x A100
GPU VRAM: 640GB
System RAM: 1024GB
Storage: 2TB
Operating System: Linux
Large enterprise deployment
High Performance:
Use Case: Enterprise serving
GPU Minimum: 8x H100
GPU VRAM: 640GB
System RAM: 2048GB
Storage: 3TB
Operating System: Linux
Maximum performance deployment
Model Deployment Readiness
Model Ecosystem Support
12%
Platforms
17%
Features
0%
Downloads
20%
Platform Compatibility
17%
Supported across 2 of 12 platforms
Context Window
Industry-standard context window comparison
4,096
tokens
4K
4K
32K
128K
1M
2M
Database Rank
#72
Percentile
Top 29%
Capacity
Small
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
MMLU
|
Knowledge | 70.0 % | 2024 |
|
HumanEval
|
Coding | 40.2 % | 2024 |
Highest Benchmark
MMLU
70.0%
Benchmarks Available
2
Latest Evaluation
Jun 2024
