Skip to content

NVIDIA · Chat

Nemotron 3.5 Lightning 30B A3B

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (7 Nov 2026).
From Requesty's listing:
NVIDIA Nemotron 3.5 Lightning 30B-A3B is a hybrid Mamba-2 + MoE + Attention model with 30B total and 3B active parameters, pre-trained on over 20T tokens with an NVFP4 recipe and Multi-Token Prediction for fast generation. Up to 1M token context for long-running autonomous agents, sub-agent workhorse deployments, and agentic workflows. Supports reasoning and tool calling. English and coding languages plus Spanish, French, German, Italian, and Japanese. Open weights under the OpenMDW License Agreement v1.1. Part of the NVIDIA Nemotron family.
llminfo IQ
114.4
Market median price
$0.10 blended / 1M
Max context
1M
Listings
19

Evidence and sources

🤗 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4llminfo IQ 114.4, ranked among chat models. From 121 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 91.7, 95% interval 70–114. From 10 benchmark families across 5 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (30.6). Costs more per task than its benchmark results predict. From 14 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 1 Aug 2026Maker HQ: US (source)
Sources: LMArena data, Crusoe Managed Inference, flex.ai API data, LiteLLM data, Models.dev data, Requesty data, Hugging FacePrimary data from LMArena from Crusoe Managed Inference: name from flex.ai API: hugging face id from LiteLLM: deprecation date from Models.dev: weights availability from Requesty: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 8 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (7 Nov 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Perplexityperplexity/perplexity/nemotron-3.5-lightning-30b-a3bSource: LiteLLM dataNot published by the provider$0.0115cache read $0.0012$0.17
 Hugging FaceInference by Fireworks AInvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · bf16Source: Hugging Face Inference Providers data262K$0.05$0.20
 CrusoeNemotron 3.5 Lightning 30B A3BSource: Crusoe Managed InferenceNot published by the provider$0.05cache read $0.03$0.20
 Fireworks AIaccounts/fireworks/models/nemotron-lightning-3p5-30b-a3bSources: Fireworks AI data, LiteLLM data262K$0.05cache read $0.01$0.20
 Runinfranvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · bf16Source: Models.dev data262K$0.05cache read $0.01$0.15
 Microsoft Azureazure_ai/FW-Nemotron-Lightning-3.5-30B-A3BSource: LiteLLM data262K$0.06cache read $0.01$0.22
 FlexaiRegions: 🇪🇺 euNVIDIA-Nemotron-3.5-Lightning-30B-A3BSources: flex.ai API data, flex.ai Pricing1M$0.06cache read $0.009$0.16
 Pioneernvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · bf16Sources: Models.dev data, Pioneer data66K$0.07cache read $0.035$0.20cache write $0.07
 Weights & Biasesnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3BSources: LiteLLM data, Models.dev data, Weights & Biases Inference data262K$0.07cache read $0.04$0.20
 Gmicloudgmi/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · bf16Source: LiteLLM data66K$0.15cache read $0.05$1.00
Show all 16 listings

Showing 10 of 16: the cheapest per 1M input tokens from each provider.

Also sold by Flowdot, Requesty, Thinking Machines.

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO49 related benchmarks · 49 results
Source: LMArena data · Nov 2026
BenchmarkNVFP4
Arena ELO
Chinese
Creative Writing
English
Show 45 more benchmarksHide 45 benchmarks
BenchmarkNVFP4
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Text Factuality - Spanish

Coding

SciCode2 results
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official release table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
agentic-coding figure · unmodified system prompt · standard harness configuration
NeMo Evaluator release-table setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ValsSource: Vals AI

General

Agentic

BrowseComp2 results
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official release table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GDPval-AA v2GDPval-AA-V2 · official release table · Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
agentic-coding figure · unmodified system prompt · standard harness configuration
NeMo Evaluator release-table setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Multilingual

Instruction following

IFBench2 results
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Reasoning

Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
text-only · no tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

Knowledge

MMLU-Pro2 results
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official release table
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Long context

Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official release table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

PinchBench3 related benchmarks · 3 results
v2 · Best Success Rate
Reported by PinchBench · via BenchBoard docs
OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · best run
v2 · Average Success Rate
Reported by PinchBench · via BenchBoard docs
OpenClaw · PinchBench v2.0.0 · task count: 147 on live leaderboard / 148 in v2.0.0 release notes · average across 6 runs
Version/Metric Unspecified
Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official table · version/metric not stated
ValsSource: Vals AI
τ³-Bankingofficial release table · Reported by NVIDIA · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Data credits: SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · LMArena, CC BY 4.0 (licence) · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Hugging Face official benchmark leaderboards; licence varies by benchmark

Also known as: accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b, azure_ai/fw-nemotron-lightning-3.5-30b-a3b, fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b, fireworks_ai/nemotron-lightning-3p5-30b-a3b, gmi/nvidia/nvidia-nemotron-3.5-lightning-30b-a3b-bf16, nemotron-3-5-lightning-30b-a3b, nemotron-lightning-3.5-30b-a3b, nvidia-nemotron-3.5-lightning-30b-a3b, nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4, nvidia/nemotron-3.5-lightning-30b-a3b, nvidia/nvidia-nemotron-3.5-lightning-30b-a3b, nvidia/nvidia-nemotron-3.5-lightning-30b-a3b-bf16, nvidia_nim/nvidia/nemotron-3.5-lightning-30b-a3b, perplexity/nemotron-3.5-lightning-30b-a3b, wandb/nvidia/nvidia-nemotron-3.5-lightning-30b-a3b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works