Compare/Jamba 1.6 Mini vs Llama Nemotron Super 49B v1.5 (Non-reasoning)

Jamba 1.6 MinivsLlama Nemotron Super 49B v1.5 (Non-reasoning)

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

AI21 Labs

Jamba 1.6 Mini

Input
$0.2/M
Output
$0.4/M
Speed
182 tok/s
TTFT
0.74s
NVIDIA

Llama Nemotron Super 49B v1.5 (Non-reasoning)

Input
$0.4/M
Output
$0.4/M
Speed
52 tok/s
TTFT
0.26s

Winner by Category

Cheaper
Jamba 1.6 Mini
Faster (tok/s)
Jamba 1.6 Mini
Lower Latency
Llama Nemotron Super 49B v1.5 (Non-reasoning)
Benchmarks (1-10)
Llama Nemotron Super 49B v1.5 (Non-reasoning)

Pricing Comparison

MetricJamba 1.6 MiniLlama Nemotron Super 49B v1.5 (Non-reasoning)
Input ($/M tokens)$0.2$0.4
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
Jamba 1.6 Mini$0.24
Llama Nemotron Super 49B v1.5 (Non-reasoning)$0.44

Speed Comparison

Output Speed (tokens/s) — higher is better
Jamba 1.6 Mini
182 tok/s
Llama Nemotron Super 49B v1.5 (Non-reasoning)
52 tok/s
Time to First Token (seconds) — lower is better
Jamba 1.6 Mini
0.74s
Llama Nemotron Super 49B v1.5 (Non-reasoning)
0.26s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
2.68.7
Coding Index
Math Index
8.0
GPQA Diamond
30.0%48.1%
MMLU-Pro
36.7%69.2%
LiveCodeBench
7.1%29.0%
AIME 2025
8.0%
MATH-500
25.7%77.0%
Humanity's Last Exam
4.6%4.3%
SciCode
10.1%23.8%
IFBench
32.9%
TerminalBench
3.8%
Jamba 1.6 Mini1 wins
10 winsLlama Nemotron Super 49B v1.5 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Jamba 1.6 Mini or Llama Nemotron Super 49B v1.5 (Non-reasoning)?

Jamba 1.6 Mini is cheaper overall. Its blended price (3:1 input/output ratio) is $0.25/M tokens vs $0.40/M for Llama Nemotron Super 49B v1.5 (Non-reasoning).

Which model performs better on benchmarks?

Llama Nemotron Super 49B v1.5 (Non-reasoning) wins 10 out of 12 benchmarks compared to 1 for Jamba 1.6 Mini. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Jamba 1.6 Mini generates tokens faster at 182 tok/s vs 52 tok/s. However, Llama Nemotron Super 49B v1.5 (Non-reasoning) has lower time-to-first-token (0.26s vs 0.74s).

When should I use Jamba 1.6 Mini vs Llama Nemotron Super 49B v1.5 (Non-reasoning)?

Choose based on your priorities: Jamba 1.6 Mini for lower cost, Llama Nemotron Super 49B v1.5 (Non-reasoning) for stronger benchmark performance, and Jamba 1.6 Mini for faster generation. For latency-sensitive apps, check the TTFT comparison above.