Skip to content
aiqbench

Nvidia · model passport

Nvidia Nemotron 3 5 Lightning 30b A3b Nvfp4

nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4
  • Open weights
  • OpenMDW-1.1 licence
  • 17.8B params
  • Released 2026-08-04(HF repo created)
5/27axes covered
Overall · LMArena
1,351#200 of 396
Best percentile
55.5Coding
Cohort standing
45.5median 60.1

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 6.4 pct — Factuality Arena (1,366)

Uneven: 49.1 percentile points between its best and worst axis — 55.5 pct on Coding versus 6.4 pct on Factuality Arena.

  • Coding55.5 pct1,425Verify →
  • Instruction following51.3 pct1,344Verify →
  • Hard prompts51 pct1,373Verify →
  • Overall49.7 pct1,351Verify →
  • Factuality Arena6.4 pct1,366Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositorynvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
Parameters17.8B
ArchitectureNemotronHForCausalLM
LicenceOpenMDW-1.1

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 stands at 45.5 (raw mean 42.8) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 stands at 45.5 versus a cohort median of 60.1 across 192 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →