Compare / Ripple 65B Preview vs Nemotron 3.5 Bolt 74B-A9B
Ripple 65B Preview vs Nemotron 3.5 Bolt 74B-A9B
Updated November 2026
Verdict
Ripple 65B Preview and Nemotron 3.5 Bolt 74B-A9B are roughly tied on the Small LM Index (74.6 vs 74.2). On the 4 benchmarks both labs report, Ripple 65B Preview wins 2 and Nemotron 3.5 Bolt 74B-A9B wins 2. Ripple 65B Preview is smaller: it needs about 41.9 GB of memory at 4-bit, against 46.9 GB for Nemotron 3.5 Bolt 74B-A9B. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Ripple 65B Preview if…
- you build agents that call tools
- you have limited memory (about 41.9 GB at 4-bit)
- you work with long documents
- you need a permissive license (Apache-2.0)
Pick Nemotron 3.5 Bolt 74B-A9B if…
- you need image input
Specifications
| Ripple 65B Preview | Nemotron 3.5 Bolt 74B-A9B | |
|---|---|---|
| Small LM Index | 74.6 (likely 74–77) | 74.2 (likely 70–79) |
| Lab | Ricursive Intelligence · Other | NVIDIA · United States |
| Released | 2026-11-04 | 2026-10-12 |
| Parameters | 64.8B (dense) | 74B (9B active, MoE) |
| Memory at 4-bit | ~41.9 GB | ~46.9 GB |
| Context window | 1M tokens | 262K tokens |
| Input | text | text, image |
| Reasoning | Always thinks | Hybrid (thinking on/off) |
| License | Apache-2.0 | OpenMDW-1.1 |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 15K | 8.9K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Ripple 65B Preview | Nemotron 3.5 Bolt 74B-A9B |
|---|---|---|
| MMLU-Pro Knowledge | 84.2 | ≈ 86 |
| GPQA Diamond Knowledge | 85.2 | 88.8 |
| Humanity's Last Exam Reasoning | ≈ 18 | 24.7✓ |
| AIME Math | 98.3 | ≈ 98 |
| SWE-bench Verified Coding | 76.5 | ≈ 68 |
| Terminal-Bench Agentic | 80.5 | 53.9 |
| IFBench Instruction following | 79.2 | — |
| MMLU Knowledge | 89.6 | — |
| HMMT Math | 90.5 | — |
| AA-LCR Long context | 75.0 | 69.7✓ |
| SciCode Coding | 39.4 | 39.7✓ |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Ripple 65B Preview or Nemotron 3.5 Bolt 74B-A9B?
Ripple 65B Preview and Nemotron 3.5 Bolt 74B-A9B are roughly tied on the Small LM Index (74.6 vs 74.2). On the 4 benchmarks both labs report, Ripple 65B Preview wins 2 and Nemotron 3.5 Bolt 74B-A9B wins 2.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Ripple 65B Preview is smaller: it needs about 41.9 GB of memory at 4-bit, against 46.9 GB for Nemotron 3.5 Bolt 74B-A9B.
Which has the longer context window?
Ripple 65B Preview has the longer context window: 1M tokens against 262K.
Can I use Ripple 65B Preview and Nemotron 3.5 Bolt 74B-A9B commercially?
Ripple 65B Preview is released under Apache-2.0 and Nemotron 3.5 Bolt 74B-A9B under OpenMDW-1.1. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.
Related comparisons
- K2-V2 Instruct vs Ripple 65B Preview
- DeepSeek-R1-Distill-Llama-70B vs Ripple 65B Preview
- Llama 3.3 70B vs Ripple 65B Preview
- Kimi Linear 48B-A3B vs Ripple 65B Preview
- DeepSeek-R1-Distill-Llama-70B vs Nemotron 3.5 Bolt 74B-A9B
- Llama 3.3 70B vs Nemotron 3.5 Bolt 74B-A9B
- Kolibri-1 vs Nemotron 3.5 Bolt 74B-A9B
- K2-V2 Instruct vs Nemotron 3.5 Bolt 74B-A9B
- Nemotron 3.5 Bolt 74B-A9B vs Qwen3-Next 80B-A3B Thinking
- Nemotron 3.5 Bolt 74B-A9B vs Qwen3-Coder-Next