Compare / Nemotron 3.5 Bolt 74B-A9B vs K2-V2 Instruct
Nemotron 3.5 Bolt 74B-A9B vs K2-V2 Instruct
Updated November 2026
Verdict
Nemotron 3.5 Bolt 74B-A9B scores higher on the Small LM Index: 73.3 vs 57.9. On the 1 benchmark both labs report, Nemotron 3.5 Bolt 74B-A9B wins 1 and K2-V2 Instruct wins 0. Both need about 47 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Nemotron 3.5 Bolt 74B-A9B if…
- you want the strongest model overall
- you need image input
Pick K2-V2 Instruct if…
- you work with long documents
- you need a permissive license (Apache-2.0)
Specifications
| Nemotron 3.5 Bolt 74B-A9B | K2-V2 Instruct | |
|---|---|---|
| Small LM Index | 73.3 (likely 72–75) | 57.9 (likely 54–62) |
| Lab | NVIDIA · United States | LLM360 / MBZUAI (K2) · Other |
| Released | 2026-10-12 | 2025-12-03 |
| Parameters | 74B (9B active, MoE) | 70B (dense) |
| Memory at 4-bit | ~46.9 GB | ~47 GB |
| Context window | 262K tokens | 512K tokens |
| Input | text, image | text |
| Reasoning | Hybrid (thinking on/off) | Hybrid (thinking on/off) |
| License | OpenMDW-1.1 | Apache-2.0 |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 7.7K | 1.2K |
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 | Nemotron 3.5 Bolt 74B-A9B | K2-V2 Instruct |
|---|---|---|
| GPQA Diamond Knowledge | 88.8 | 69.3 |
| Humanity's Last Exam Reasoning | 28.7 | ≈ 9 |
| AIME Math | ≈ 95 | 80.2 |
| Terminal-Bench Agentic | 53.9 | — |
| IFEval Instruction following | — | 90.0 |
| HMMT Math | — | 71.4 |
| AA-LCR Long context | 67.4 | — |
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, Nemotron 3.5 Bolt 74B-A9B or K2-V2 Instruct?
Nemotron 3.5 Bolt 74B-A9B scores higher on the Small LM Index: 73.3 vs 57.9. On the 1 benchmark both labs report, Nemotron 3.5 Bolt 74B-A9B wins 1 and K2-V2 Instruct wins 0.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 47 GB of memory at 4-bit quantization.
Which has the longer context window?
K2-V2 Instruct has the longer context window: 512K tokens against 262K.
Can I use Nemotron 3.5 Bolt 74B-A9B and K2-V2 Instruct commercially?
Nemotron 3.5 Bolt 74B-A9B is released under OpenMDW-1.1 and K2-V2 Instruct under Apache-2.0. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.