Compare/NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Granite 4.0 H Small

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)vsGranite 4.0 H Small

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

Input
$0.06/M
Output
$0.24/M
Speed
138 tok/s
TTFT
1.00s
IBM

Granite 4.0 H Small

Input
$0.06/M
Output
$0.25/M
Speed
524 tok/s
TTFT
8.68s

Winner by Category

Cheaper
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Faster (tok/s)
Granite 4.0 H Small
Lower Latency
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Benchmarks (11-0)
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

Pricing Comparison

MetricNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)Granite 4.0 H Small
Input ($/M tokens)$0.06$0.06
Output ($/M tokens)$0.24$0.25
Cost for 1M input + 100K output tokens:
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)$0.08
Granite 4.0 H Small$0.08

Speed Comparison

Output Speed (tokens/s) — higher is better
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
138 tok/s
Granite 4.0 H Small
524 tok/s
Time to First Token (seconds) — lower is better
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
1.00s
Granite 4.0 H Small
8.68s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
24.310.8
Coding Index
19.08.5
Math Index
91.013.7
GPQA Diamond
75.7%41.6%
MMLU-Pro
79.4%62.4%
LiveCodeBench
74.1%25.1%
AIME 2025
91.0%13.7%
MATH-500
Humanity's Last Exam
10.2%3.7%
SciCode
29.6%20.9%
IFBench
71.1%31.5%
TerminalBench
13.6%2.3%
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)11 wins
0 winsGranite 4.0 H Small

Frequently Asked Questions

Which is cheaper, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) or Granite 4.0 H Small?

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.10/M tokens vs $0.11/M for Granite 4.0 H Small.

Which model performs better on benchmarks?

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) wins 11 out of 12 benchmarks compared to 0 for Granite 4.0 H Small. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Granite 4.0 H Small generates tokens faster at 524 tok/s vs 138 tok/s. NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) also has lower time-to-first-token (1.00s vs 8.68s).

When should I use NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Granite 4.0 H Small?

Choose based on your priorities: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) for lower cost, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) for stronger benchmark performance, and Granite 4.0 H Small for faster generation. For latency-sensitive apps, check the TTFT comparison above.