NVIDIA

Nemotron 3.5 Lightning 30B

Generally availableOpen weights262K contextReasoning

Summary

Nemotron 3.5 Lightning 30B is an open-weight language model from NVIDIA, released on 11 Aug 2026. It accepts text and generates text, with a 262K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.06 per million input tokens and $0.16 per million output tokens (Vercel AI Gateway), across 4 providers we track.

Nemotron model for efficient reasoning, coding, and specialized AI agents

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperNVIDIA
Release date11 Aug 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseopenmdw-1.1 [Hugging Face]
Parameters31.6B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoffSept 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facenvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 [Hugging Face]

Nemotron 3.5 Lightning 30B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
NVIDIA NIM
nvidia/nemotron-3.5-lightning-30b-a3b
FreeFree–262Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
nvidia/nemotron-3.5-lightning-free
FreeFree–1Mmodels.dev, 18 Nov 2026
Nebius AI Studio
nvidia/Nemotron-3_5-Lightning
$0.06$0.24$0.061Mmodels.dev, 18 Nov 2026
Vercel AI Gateway
nvidia/nemotron-3.5-lightning
$0.06$0.16$0.03262Kmodels.dev, 18 Nov 2026
OpenRouter
nvidia/nemotron-3.5-lightning
$0.07$0.20$0.04262KOpenRouter, 18 Nov 2026

Running Nemotron 3.5 Lightning 30B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)19 GB20 GB22 GB
Q8_0 (8-bit)34 GB35 GB36 GB
FP16 / BF16 (16-bit)63 GB64 GB66 GB

At 4-bit with an 8K conversation, Nemotron 3.5 Lightning 30B needs about 20 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Nemotron 3.5 Lightning 30B?

Nemotron 3.5 Lightning 30B has a context window of 262,144 tokens (262K) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the Nemotron 3.5 Lightning 30B API cost?

Nemotron 3.5 Lightning 30B is listed from $0.06 per million input tokens and $0.16 per million output tokens (Vercel AI Gateway). Prices last verified 18 Nov 2026.

Is Nemotron 3.5 Lightning 30B open source?

Nemotron 3.5 Lightning 30B is an open-weight model: its weights are published on Hugging Face as nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 under the openmdw-1.1 license. Check the license terms before commercial use.

When was Nemotron 3.5 Lightning 30B released?

NVIDIA released Nemotron 3.5 Lightning 30B on 11 Aug 2026, according to models.dev.

Which providers offer Nemotron 3.5 Lightning 30B?

We track Nemotron 3.5 Lightning 30B on 4 providers: NVIDIA NIM, Vercel AI Gateway, Nebius AI Studio, OpenRouter.

How much VRAM does Nemotron 3.5 Lightning 30B need?

About 20 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 35 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Ling 3.0 Flash VLInclusionai10 Sept 2026256K$0.06$0.18Open
Ling 3.0 Flash FinInclusionai27 Aug 2026256K$0.07$0.22Open
Ternary Bonsai 2 9BPrism ML16 Oct 2026262K$0.08$0.13Open
Nex-N2.5-ProNEX AGI8 Sept 2026262K$0.07$0.25Open
Nex-N2.5-MiniNEX AGI8 Sept 2026262K$0.03$0.10Open
LFM3-1.7BLiquid6 Nov 2026262K$0.08$0.20Open

Change history

  • Max output changed from 262K to 131K
  • Name changed from Nemotron 3.5 Lightning 30B A3B to Nemotron 3.5 Lightning 30B
  • Max output changed from 236K to 262K
  • Max output changed from 262K to 236K
  • Max output changed from 1M to 262K
  • Context window changed from 1M to 262K
  • Max output changed from 262K to 1M
  • Context window changed from 262K to 1M
  • Max output changed from 131K to 262K
  • Name changed from Nemotron 3.5 Lightning 30B to Nemotron 3.5 Lightning 30B A3B
  • Max output changed from 1M to 131K
  • Context window changed from 1M to 262K
  • Name changed from Nemotron 3.5 Lightning 30B A3B to Nemotron 3.5 Lightning 30B
  • Name changed from Nemotron 3.5 Lightning 30B to Nemotron 3.5 Lightning 30B A3B
  • Context window changed from 262K to 1M
  • Max output changed from 131K to 1M
  • Max output changed from 1M to 131K
  • Name changed from Nemotron 3.5 Lightning 30B A3B to Nemotron 3.5 Lightning 30B
  • Context window changed from 1M to 262K
  • Context window changed from 262K to 1M
  • Max output changed from 262K to 1M
  • Max output changed from 236K to 262K
  • Vercel AI Gateway price changed: input $0.05 → $0.06, output $0.20 → $0.16 per 1M tokens
  • Max output changed from 1M to 236K
  • Context window changed from 1M to 262K

Sources