Nemotron 3.5 Lightning 30B A3B NVFP4 released
NVIDIA · Model release
Source confirmed
Data as of September 24, 2026 · How the score is built
CurrentOpen WeightReasoning
Released Aug 11, 20261M contextNVIDIA Nemotron 3.5 Lightning model card
Nemotron 3.5 Lightning 30B A3B NVFP4
Decision readingNemotron 3.5 Lightning 30B A3B NVFP4 scores 19.1 out of 100 and ranks #186 of 194. This profile shows 13 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #67. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Released Aug 11, 2026 — see all recent releases
Nemotron 3.5 Lightning 30B A3B NVFP4 will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
19.1/100
field median 50.2#186 of 194 ranked models
Public
#186of 194
Verified —
Price
Self-hosted; infrastructure cost varies
input median $0.97No comparable first-party hosted token rate
Speed
Not measured
field median 91 tok/sTime to first token not measured
Context
1Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Instruction Following ranks #67. A well-rounded choice across a range of tasks.
Validate before choosing
13 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 13 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #104 of 105Percentile 1stWeight 22%4 benchmarksVerified | 7.3 | 4 benchmarks | Verified | |||
| CodingRank #135 of 135Percentile 0thWeight 20%4 benchmarksVerified | 11.4 | 4 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #154 of 158Percentile 3rdWeight 12%4 benchmarksVerified | 20.7 | 4 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #67 of 124Percentile 46thWeight 5%1 benchmarkVerified | 68.5 | 1 benchmark | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
13 of 483 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic4/4 verified
- Coding4/4 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge4/4 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- MathNot measured
Verified sourceProvisionalNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Nemotron 3.5 Lightning 30B A3B NVFP4 category percentile values
- Agentic1st percentile
- Coding0th percentile
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge3rd percentile
- MultilingualNot eligible
- Instruction following46th percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#104/105
- Coding#135/135
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#154/158
- MultilingualNot ranked
- Inst. Following#67/124
- MathNot ranked
Top decileTop quartileMid-fieldNot eligible
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SciCodeScientific Code Benchmark | Score31.4% | Versus best verified row Best verified: Sakana Fugu · 60.1% | Gap28.7 behind | Weight10% ref. weight | Provider exact |
| SWE Multilingual | Score36.5% | Versus best verified row Best verified: Claude Opus 5.5 · 93.9% | Gap57.4 behind | Weight5% ref. weight | Provider exact |
| Terminal-Bench 2.1 | Score23.5% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap69.3 behind | WeightScored in Agentic | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score52.8% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap43.2 behind | WeightDisplay only | Provider exact |
Agentic4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score23.5% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap69.3 behind | Weight8% ref. weight | Provider exact |
| BrowseComp | Score36.8% | Versus best verified row Best verified: Atria Dawn Preview · 92.5% | Gap55.7 behind | Weight8% ref. weight | Provider exact |
| τ³-bench resultsτ³-Bench Tool-Agent-User Evaluation | Score9.5% | Versus best verified row Best verified: Mercury 2.5 · 96.0% | Gap86.5 behind | Weight2% ref. weight | Provider exact |
| PinchBench | Score83.4% | Versus best verified row Best verified: Pokee-Isaac 28B · 95.7% | Gap12.2 behind | WeightDisplay only | Provider exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLE w/o toolsHumanity's Last Exam without tools | Score10.5% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap53.9 behind | Weight7% ref. weight | Provider exact |
| MMLU-ProMassive Multitask Language Understanding Professional | Score81.6% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap8 behind | Weight6% ref. weight | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score75.6% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap20.4 behind | Weight3% ref. weight | Provider exact |
| GPQA-DGPQA Diamond | Score75.6% | Versus best verified row Best verified: GPT-6 Astra · 96.0% | Gap20.4 behind | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFBenchInstruction Following Benchmark | Score72.9% | Versus best verified row Best verified: MAI-Thinking-1 · 85% | Gap12.1 behind | WeightWeighted 70% | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 13 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
30b-a3b-nvfp4 · NVFP4
Radar
Full release historyNemotron 3.5 Lightning 30B A3B NVFP4 release history
Radar confirmed these at the source. Use Nemotron 3.5 Lightning 30B A3B NVFP4 in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedNVIDIA Nemotron 3.5 Lightning model card
- Context window
- 1MNVIDIA Nemotron 3.5 Lightning model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Open NVFP4 checkpoint for self-hosted inference; NVIDIA documents deployments on DGX Spark, H100, and other supported NVIDIA hardware.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordNVIDIA Nemotron 3.5 Lightning model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #186 of 194 on the public leaderboard with a score of 19.1/100. It does not yet have enough sourced coverage for a verified position.
Nemotron 3.5 Lightning 30B A3B NVFP4 is a open weight model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open NVFP4 checkpoint for self-hosted inference; NVIDIA documents deployments on DGX Spark, H100, and other supported NVIDIA hardware.
13 of 483 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #67, while its lowest eligible position is Knowledge at #154. a well-rounded choice across a range of tasks.
Last updated September 24, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Nemotron 3.5 Lightning 30B A3B NVFP4 perform overall in AI benchmarks?
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #186 out of 194 models on the public BenchAlign leaderboard, with a score of 19.1/100. Its evidence status is Estimated, and this profile shows 13 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Nemotron 3.5 Lightning 30B A3B NVFP4 good for knowledge and understanding?
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #154 out of 158 eligible models for knowledge and understanding, with a public category score of 20.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Nemotron 3.5 Lightning 30B A3B NVFP4 good for coding and programming?
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #135 out of 135 eligible models for coding and programming, with a public category score of 11.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Nemotron 3.5 Lightning 30B A3B NVFP4 good for agentic tool use and computer tasks?
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #104 out of 105 eligible models for agentic tool use and computer tasks, with a public category score of 7.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Nemotron 3.5 Lightning 30B A3B NVFP4 good for instruction following?
Nemotron 3.5 Lightning 30B A3B NVFP4 ranks #67 out of 124 eligible models for instruction following, with a public category score of 68.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Nemotron 3.5 Lightning 30B A3B NVFP4 open source?
Nemotron 3.5 Lightning 30B A3B NVFP4 is an open-weight model from NVIDIA. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Nemotron 3.5 Lightning 30B A3B NVFP4 have full benchmark coverage on BenchLM?
No. Nemotron 3.5 Lightning 30B A3B NVFP4 currently has 27 source-displayable rows across 483 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Nemotron 3.5 Lightning 30B A3B NVFP4?
Nemotron 3.5 Lightning 30B A3B NVFP4 has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.