Terminal-interaction specialization
According to the model card, the Nemotron-Terminal family is specialized for autonomous terminal interaction and uses the Nemotron-Terminal-Corpus terminal-task dataset.
Open Source Model Profile · nvidia
Nemotron-Terminal-8B
Nemotron-Terminal-8B is an 8.19B-parameter Qwen3 text-generation fine-tune from NVIDIA for autonomous terminal interaction.
- Publisher
- nvidia
- Task
- text-generation
- Model type
- qwen3
- License
- nvidia-open-model-license
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Nemotron-Terminal-8B is published by nvidia as a text-generation fine-tune. Captured configuration identifies Qwen3ForCausalLM with a qwen3 model type, and Safetensors metadata reports 8,190,735,360 parameters. According to the model card, it is the 8B member of the Nemotron-Terminal family for autonomous terminal interaction.
Recorded capabilities
Publisher-reported Terminal-Bench gains
The model card reports 13.0% accuracy for the 8B variant on Terminal-Bench 2.0 against a 2.47% baseline figure.
Terminus 2 JSON workflow
The model card says training uses Terminus 2 scaffolding with structured JSON output and recommends Terminus 2 for evaluation consistency.
Qwen3 8B-class foundation
Captured configuration records Qwen3ForCausalLM with a qwen3 model type at about 8.19B parameters.
Use cases in the source record
- Autonomous terminal-interaction trials using the publisher-documented Terminus 2 scaffolding and structured JSON output.
- Terminal-Bench 2.0 evaluation work following the card's guidance to use Terminus 2 scaffolding for consistency.
Limitations and unknowns
- No context-window value was extracted from this record.
- Provider state is historical snapshot data and should be refreshed before being presented as current availability.
- Benchmark figures come from the publisher model card and have not been independently measured or verified by Ethen.
- No pricing, VRAM, latency, or supported-language values were extracted from this record.
Source and provenance
Source: nvidia/Nemotron-Terminal-8B
Captured: Unknown. Processed: 2026-09-07T19:35:59.360417+00:00.
Nemotron-Terminal Model Family Nemotron-Terminal is a family of models specialized for autonomous terminal interaction, fine-tuned from the Qwen3 (8B, 14B, and 32B). Developed by NVIDIA, these models utilize Nemotron-Terminal-Corpus , a large-scale open-source dataset for terminal tasks, to achieve performance that rivals frontier models many times their size. Model Variants We release the following variants of the Nemotron-Terminal family: Nemotron-Terminal-8B Nemotron-Terminal-14B Nemotron-Terminal-32B Performance on Terminal-Bench 2.0 The Nemotron-Terminal family demonstrates profound leaps in capability compared to the Qwen3 bas…
F001F002F003F004F005F006F010F011F012F013F014F015