Skip to content

All Models

Rank #12 / 13

Nemotron 3 Nano Omni 30B-A3B

Nemotron 3 Nano Omni 30B-A3B is NVIDIA's Nemotron model (open weights). It is ranked 12 of 13 models with enough coverage on the Visual Intelligence Index.

  • NVIDIA
  • Open weights
  • Nemotron
  • Video input
  • Audio
  • Structured output
  • Tool calling
  • Streaming
  • Batch API
  • Self-hostable
Read the report
57.5%Visual Intelligence Index · Rank #12 of 13

Capability profile

Comparison Summary

Nemotron 3 Nano Omni 30B-A3B ranks 12 of 13 on the perception index. Immediately ahead is Qwen3.5-35B-A3B. Immediately behind is Molmo 2 8B. List price is $0.15 per million input tokens and $0.60 per million output. 1 of 13 listed models cost less to prompt. Latency is 5.9s with a 128K context window and tokens/s. Prices and most scores in this snapshot are placeholders, not sourced figures. Strongest capability in this set is Causal Reasoning (63%). Weakest is Action / Event Understanding (55%).

Visual Intelligence
59.8%
Availability
Open weights
Input / 1M tokens
$0.15
Output / 1M tokens
$0.60
Latency
5.9s
Context Window
128K
Speed (tokens/s)
Parameters
30B
Time to first token

All benchmark scores

BenchmarkMetricScore95% CISettingSource
Video-MME v2Accuracy, no subtitles35.0%33.3–36.61 fps, 727-frame cap (254 videos thinned)Reported
LVBenchTest accuracy54.2%51.7–56.71 fps, 727-frame cap (103 videos thinned)Reported
Perception TestOverall accuracy70.3%66.0–74.51 fpsReported
NExT-QAAccuracy (hard split)81.2%80.1–82.21 fpsReported
Q-Bench VideoOverall accuracy64.9%61.7–68.01 fpsReported
EgoSchemaAccuracy (fullset)65.8%61.6–70.01 fpsReported
UCF101-ADAccuracy31.0%29.6–32.41 fpsReported

Benchmark Scores

Compare reported model scores across each available benchmark or capability index.

13 of 13 models
Filter by model access

Display

Capabilities Index Scores

Compare reported model scores across each available benchmark or capability index.

13 of 13 models
Filter by model access

Display

Usability

5.0/ 5

What it's like to build against this model, scored out of five from the developer-facing capabilities in the dataset.

Reachable1.0

There is an endpoint you can call without hosting anything.

  • First-party API — supported
  • Third-party API — supported
Portable1.0

You can run it yourself, and are not tied to one vendor.

  • Open weights — supported
  • Self-hostable — supported
Multimodal input1.0

It takes the footage directly, rather than frames you extracted.

  • Video ingestion — supported
  • Audio — supported
Programmable1.0

Output you can parse, and tools it can call on its own.

  • Structured output — supported
  • Tool calling — supported
Operable1.0

Usable interactively and in bulk, not only one call at a time.

  • Streaming — supported
  • Batch API — supported

Other NVIDIA models

Other models from the NVIDIA family.

DateModelVisual IntelligenceLatency
Jun 18, 2026Nemotron 3 Nano Omni 30B-A3B59.8%5.9s