Compare / Nemotron 3.5 Bolt 74B-A9B vs Kolibri-1

Nemotron 3.5 Bolt 74B-A9B vs Kolibri-1

Updated November 2026

Verdict

Nemotron 3.5 Bolt 74B-A9B scores higher on the Small LM Index: 73.3 vs 68.3. On the 3 benchmarks both labs report, Nemotron 3.5 Bolt 74B-A9B wins 3 and Kolibri-1 wins 0. Nemotron 3.5 Bolt 74B-A9B is smaller: it needs about 46.9 GB of memory at 4-bit, against 49.6 GB for Kolibri-1. 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 mostly write code
you build agents that call tools
you have limited memory (about 46.9 GB at 4-bit)
you need image input

Pick Kolibri-1 if…

you work with long documents
you need a permissive license (Apache-2.0)

Specifications

	Nemotron 3.5 Bolt 74B-A9B	Kolibri-1
Small LM Index	73.3 (likely 72–75)	68.3 (likely 67–70)
Lab	NVIDIA · United States	Aleph Alpha · Europe
Released	2026-10-12	2026-10-03
Parameters	74B (9B active, MoE)	78.1B (3.5B active, MoE)
Memory at 4-bit	~46.9 GB	~49.6 GB
Context window	262K tokens	1M tokens
Input	text, image	text
Reasoning	Hybrid (thinking on/off)	Always thinks
License	OpenMDW-1.1	Apache-2.0
API price / 1M tokens	Self-host only	Self-host only
Hugging Face downloads (30 days)	7.7K	22.8K

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	Kolibri-1
MMLU-Pro Knowledge	≈ 86	80.0
GPQA Diamond Knowledge	88.8	84.3
Humanity's Last Exam Reasoning	28.7	21.5
AIME Math	≈ 95	96.0
LiveCodeBench Coding	≈ 84	85.9
SWE-bench Verified Coding	≈ 69	66.4
Terminal-Bench Agentic	53.9	27.7
τ²-Bench Agentic	—	80.4
IFBench Instruction following	—	78.1
BFCL Agentic	—	61.4
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 Kolibri-1?

Nemotron 3.5 Bolt 74B-A9B scores higher on the Small LM Index: 73.3 vs 68.3. On the 3 benchmarks both labs report, Nemotron 3.5 Bolt 74B-A9B wins 3 and Kolibri-1 wins 0.

Which is cheaper to run?

Neither model has a hosted API on OpenRouter, so you would run both yourself. Nemotron 3.5 Bolt 74B-A9B is smaller: it needs about 46.9 GB of memory at 4-bit, against 49.6 GB for Kolibri-1.

Which has the longer context window?

Kolibri-1 has the longer context window: 1M tokens against 262K.

Can I use Nemotron 3.5 Bolt 74B-A9B and Kolibri-1 commercially?

Nemotron 3.5 Bolt 74B-A9B is released under OpenMDW-1.1 and Kolibri-1 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.