NVIDIA · Nvidia Nemotron 3 Nano 30b A3b Bf16 · active

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is an open-weight language model published by NVIDIA.

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Statusactive
InputText
OutputText
Context256K
Total / active parameters31.6B / 3.5B
Licenseother
APIYes
Open weights / self-hostYes / Yes

Provider availability

Serving endpoints and pricing

No directly sourced provider offerings yetPricing and availability stay unknown until collected from each serving provider.

This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.

Technical specification

Developer model IDnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
VersionNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
ReleasedDec 15, 2025
ArchitectureNemotronHForCausalLM
Maximum output1M tokens
Knowledge cutoffNov 28, 2025

Capabilities

chatgenerationreasoningtools
ReasoningYes
VisionNo
Tool callingYes

Version lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16, nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Explicit unknowns

  • Provider pricing

Comparable peers

Related model comparisons

All comparisons →

Questions

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 FAQs

What is NVIDIA-Nemotron-3-Nano-30B-A3B-BF16?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is an open-weight language model published by NVIDIA. It is developed by NVIDIA and its current sourced lifecycle status is active.

What inputs and outputs does NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 support?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16's current record lists Text as input and Text as output.

How much context does NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 support?+

The current record lists a 262,144-token context window and a maximum output of 1,048,576 tokens.

Is NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 available through an API?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is marked as API-available. No directly sourced serving-provider record is attached yet.

How large is NVIDIA-Nemotron-3-Nano-30B-A3B-BF16?+

The current record lists 31.6B total parameters and 3.5B active parameters. Its architecture is NemotronHForCausalLM.

What capabilities and tasks does NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 support?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are text.

Can NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 be self-hosted?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is an open-weight model. Self-hosting is supported, and the recorded license is other.

Does NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.

Which models can NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 be compared with?+

The current compatible peer set includes NVIDIA-Nemotron-3-Super-120B-A12B-BF16, NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16, NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16, and Qwen3.8-27B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

How current is the Model Markets record for NVIDIA-Nemotron-3-Nano-30B-A3B-BF16?+

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 was last verified Aug 28, 2026 from NVIDIA's primary source, “nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 developer model repository.” The evidence is classified as official fact.

Primary evidence

Sources and observation date