NVIDIA makes this open-source chat model for text input and output. It is a post-trained small language model designed for local voice assistants, interactive personas, and embedded interfaces.
Input
Output
Context
66K
Max Output
-
Parameters
4B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Public resources
Specification sources
As of Nov 17, 2026.
Answered from the facts on this page, with their sources.
NVIDIA Nemotron 3.5 Bolt E4B 4GB has a context window of 65,536 tokens (source: Web research). A provider may serve less; Inferbase routes on what each provider serves.
Yes. NVIDIA Nemotron 3.5 Bolt E4B 4GB is an open-weight model under the Other license. You can download and self-host it within the license terms.
About 4B, read from the model's name. NVIDIA has not published an exact count.
Strengths: Supports 34 languages. Each is computed from the model's stated facts and benchmark results.
NVIDIA Nemotron 3.5 Bolt E4B 4GB accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for NVIDIA Nemotron 3.5 Bolt E4B 4GB yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves NVIDIA Nemotron 3.5 Bolt E4B 4GB, and Inferbase runs it on your account with the same routing and logs.
NVIDIA has not published a parameter count for NVIDIA Nemotron 3.5 Bolt E4B 4GB, so the catalog cannot compute its memory. The GPU planner can size it from a count you enter.
The model card of NVIDIA Nemotron 3.5 Bolt E4B 4GB lists 34 languages: English, Arabic, Bulgarian, Czech, Danish, German, Greek, Spanish, Estonian, Finnish, French, Hindi, Croatian, Hungarian, Indonesian, Italian, Japanese, Korean, Lithuanian, Latvian, Dutch, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Swedish, Thai, Turkish, Ukrainian, Vietnamese and Chinese. That is what NVIDIA states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.