Compare/Jamba 1.5 Mini vs Llama Nemotron Super 49B v1.5 (Non-reasoning)

Jamba 1.5 MinivsLlama Nemotron Super 49B v1.5 (Non-reasoning)

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

AI21 Labs

Jamba 1.5 Mini

Input
$0.2/M
Output
$0.4/M
Speed
TTFT
NVIDIA

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

Input
$0.1/M
Output
$0.4/M
Speed
51 tok/s
TTFT
0.23s

Winner by Category

Cheaper
Llama Nemotron Super 49B v1.5 (Non-reasoning)
Faster (tok/s)
Llama Nemotron Super 49B v1.5 (Non-reasoning)
Lower Latency
Jamba 1.5 Mini
Benchmarks (1-11)
Llama Nemotron Super 49B v1.5 (Non-reasoning)

Pricing Comparison

MetricJamba 1.5 MiniLlama Nemotron Super 49B v1.5 (Non-reasoning)
Input ($/M tokens)$0.2$0.1
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
Jamba 1.5 Mini$0.24
Llama Nemotron Super 49B v1.5 (Non-reasoning)$0.14

Speed Comparison

Output Speed (tokens/s) — higher is better
Jamba 1.5 Mini
Llama Nemotron Super 49B v1.5 (Non-reasoning)
51 tok/s
Time to First Token (seconds) — lower is better
Jamba 1.5 Mini
Llama Nemotron Super 49B v1.5 (Non-reasoning)
0.23s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
8.014.6
Coding Index
10.5
Math Index
8.0
GPQA Diamond
30.2%48.1%
MMLU-Pro
37.1%69.2%
LiveCodeBench
6.2%29.0%
AIME 2025
8.0%
MATH-500
35.7%77.0%
Humanity's Last Exam
5.1%4.3%
SciCode
8.0%23.8%
IFBench
32.9%
TerminalBench
3.8%
Jamba 1.5 Mini1 wins
11 winsLlama Nemotron Super 49B v1.5 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Jamba 1.5 Mini or Llama Nemotron Super 49B v1.5 (Non-reasoning)?

Llama Nemotron Super 49B v1.5 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.17/M tokens vs $0.25/M for Jamba 1.5 Mini.

Which model performs better on benchmarks?

Llama Nemotron Super 49B v1.5 (Non-reasoning) wins 11 out of 12 benchmarks compared to 1 for Jamba 1.5 Mini. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Llama Nemotron Super 49B v1.5 (Non-reasoning) generates tokens faster at 51 tok/s vs 0 tok/s. Jamba 1.5 Mini also has lower time-to-first-token (0.00s vs 0.23s).

When should I use Jamba 1.5 Mini vs Llama Nemotron Super 49B v1.5 (Non-reasoning)?

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