Guides / Made in the US
Best American open models under 100B
Updated November 2026
As of November 2026, the best option is Ternary Bonsai 2 27B by PrismML, with a Small LM Index of 74.6, followed by Nemotron 3.5 Bolt 74B-A9B (73.3) and Muse Glimmer 30B (72.6).
Models from labs based in the United States, ranked by the Small LM Index.
| # | Model | Lab | Small LM Index | Params | Memory (4-bit) | API / 1M | License |
|---|---|---|---|---|---|---|---|
| 1 | Ternary Bonsai 2 27B | PrismML | 74.6 | 27.4B | ~18.2 GB | self-host | Apache-2.0 |
| 2 | Nemotron 3.5 Bolt 74B-A9B | NVIDIA | 73.3 | 74B (9B active) | ~46.9 GB | self-host | OpenMDW-1.1 |
| 3 | Muse Glimmer 30B | Meta | 72.6 | 29.6B | ~19.2 GB | $0.53 | Apache-2.0 |
| 4 | Gemma 4 31B | 70.1 | 30.7B | ~21.9 GB | $0.16 | Apache-2.0 | |
| 5 | Gemma 4 26B-A4B | 67.5 | 25.2B (3.8B active) | ~16.8 GB | $0.068 | Apache-2.0 | |
| 6 | Granite 4.2 30B | IBM (Granite) | 67.0 | 30B | ~21.4 GB | self-host | Apache-2.0 |
| 7 | gpt-oss-20b | OpenAI | 64.0 | 20.9B (3.6B active) | ~13.8 GB | $0.020 | Apache-2.0 |
| 8 | Nemotron 3.5 Lightning | NVIDIA | 63.6 | 31.6B (3.6B active) | ~22.4 GB | $0.049 | OpenMDW-1.1 |
| 9 | Granite 4.2 8B | IBM (Granite) | 63.5 | 8B | ~6.9 GB | $0.082 | Apache-2.0 |
| 10 | Nemotron 3 Nano 30B-A3B | NVIDIA | 62.6 | 31.6B (3.5B active) | ~20.3 GB | $0.10 | NVIDIA Open Model |
| 11 | LFM2.5 24B-A2B | Liquid AI | 61.4 | 24B (2B active) | ~15.7 GB | $0.21 | LFM Open License |
| 12 | Apriel 1.6 15B Thinker | ServiceNow (Apriel) | 60.9 | 14.9B | ~11.4 GB | self-host | MIT |
| 13 | LFM3 1.7B | Liquid AI | 60.0 | 1.7B | ~1.7 GB | self-host | LFM Open License |
| 14 | Nemotron Labs Dory 1.0 4B | NVIDIA | 60.0 | 4B | ~3.4 GB | self-host | OpenMDW-1.1 |
| 15 | OLMo 3.1 32B Think | Ai2 (OLMo) | 57.0 | 32.2B | ~22 GB | self-host | Apache-2.0 |
Memory covers the weights only; long contexts need more. Scores are mostly lab-reported, so gaps of 1–2 points are noise. See the methodology, or filter the full leaderboard yourself.
Head to head
Questions
What is the best open-weight model from a US lab?
As of November 2026, the best option is Ternary Bonsai 2 27B by PrismML, with a Small LM Index of 74.6, followed by Nemotron 3.5 Bolt 74B-A9B (73.3) and Muse Glimmer 30B (72.6).
How is this list ranked?
Models from labs based in the United States, ranked by the Small LM Index.
Which of the top five needs the least memory?
Gemma 4 26B-A4B, at about 16.8 GB with 4-bit quantization.
Which is the cheapest to use through an API?
gpt-oss-20b, at $0.020 per million tokens from the cheapest provider on OpenRouter.
Other guides
- Best small open models for coding
- Best small open models for math
- Best LLMs that run on an 8 GB GPU or laptop
- Best LLMs that run on a 16 GB GPU
- Best LLMs for a 24 GB GPU (RTX 4090, RTX 3090)
- Best tiny LLMs for phones and edge devices
- Best cheap LLM APIs (open models)
- Best small open vision-language models
- Best open models with an Apache 2.0 or MIT license
- Best European open language models
- Best fully open models (open data and code)