Model Analysis

Nemotron 3 Nano Omni 30B-A3B Reasoning (Free)

openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

376.2

median tok/s

670ms TTFT

100.0% success

Throughput Runs

TTFT Runs

Avg TTFT

670ms

Avg Throughput

371.2 tok/s

Total Cost

$0.0000

Commentary

by derived

Nemotron 3 Nano Omni 30B-A3B Reasoning (Free) posts 376.2 tok/s median throughput with 670ms median TTFT across 5 runs. Success rate is 100.0% with $0.00 total spend.

Factualttft

Startup latency on ttft-factual landed in the 670ms range.

Definitionttft

Startup latency on ttft-definition landed in the 670ms range.

Data Structuresthroughput

Sustained decode speed on throughput-data-structures contributed to the 376.2 tok/s median.

Api Designthroughput

Sustained decode speed on throughput-api-design contributed to the 376.2 tok/s median.

Essaythroughput

Sustained decode speed on throughput-essay contributed to the 376.2 tok/s median.

Notable Prompts

Api Designthroughput

Fastest throughput run peaked at 416.5 tok/s.

Factualttft

Slowest startup path took 954ms to first token.

All Runs

Prompt	Type	Tok/s	TTFT	Tokens	Cost
1. Api Design throughput-api-design	throughput	416.5	3170ms	4096	$0.0000
1. Data Structures throughput-data-structures	throughput	376.2	4613ms	3956	$0.0000
1. Essay throughput-essay	throughput	320.8	4584ms	4096	$0.0000
1. Definition ttft-definition	ttft	n/a	386ms	72	$0.0000
1. Factual ttft-factual	ttft	n/a	954ms	102	$0.0000

5 runs · Throughput rows require valid long-output runs · TTFT shown for all successful runs