Nemotron H 4B Instruct 128K
NVIDIA's Nemotron H 4B Instruct 128K is a large language model optimized for chat, instruction following, and tool-calling use-cases, with a hybrid architecture combining Mamba-2, MLP, and Attention layers. It is particularly suited for tasks that require understanding and responding to instructions, as well as generating human-like text in single and multi-turn conversations.
Input
Output
Context
128K
Max Output
-
Parameters
4B
Technical Specifications
Model TypeChat
Context Window128,000 tokens
Max Output TokensNot available
Parameters4B
Release DateApr 15, 2025
Training CutoffSep 1, 2024
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Nemotron H 4B Instruct 128K
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.