Olmo 3 7B
Fully open chat model. Data and code are public. Fits on the laptop you already own, if it has 8 GB.
Model / Nous Research
Trust score 64 of 100. No, open weights with custom rules.
Short answer (as of Oct 14, 2026): Hermes 3 8B is a local AI model from Nous Research. Truly open? No, open weights with custom rules. Business use: yes, with limits. Our estimate says it needs about 8 GB of RAM. Trust score 64 of 100.
As of Oct 14, 2026: license Llama Community License; business use yes, with limits; sign-up not needed; about 8 GB RAM (estimate); trust score 64/100. Sources.
Chat and role play built on Llama 3.1.
Who makes it: Nous Research. The files come from the maker's own Hugging Face account.
License: Llama Community License. Meta's own license. You can download and use it for free, but Meta sets the rules. The Open Source Initiative says it is not open source.
Business use: Yes for most businesses. If your products had over 700 million monthly users, you need a separate deal with Meta. You must follow Meta's use policy and show "Built with Llama" if you share it.
Training data: We have not found a full public data release. Not yet checked in depth.
Pick a computer with at least 8 GB of memory. On a Mac, that is the unified memory. On a PC, a graphics card with that much VRAM is fastest. A PC with only normal RAM will also work, just slower.
NousResearch/Hermes-3-Llama-3.1-8B-GGUF.Q4_K_M. It is the best mix of size and quality for most people.The files are GGUF builds that LM Studio can load. We checked that this repo exists on Oct 14, 2026. Full LM Studio guide.
Does it fit? Yes. Its memory window is big enough for Hermes.
hermes model. Choose LM Studio and press Enter to keep http://localhost:1234/v1.hermes to start.No, open weights with custom rules. Meta's own license. You can download and use it for free, but Meta sets the rules. The Open Source Initiative says it is not open source.
Yes for most businesses. If your products had over 700 million monthly users, you need a separate deal with Meta. You must follow Meta's use policy and show "Built with Llama" if you share it.
No. Download without an account.
Our estimate is about 8 GB of RAM for a 4-bit file of about 4.8 GB. This is a rough guide, not a test.
| Fact | What we found | Status |
|---|---|---|
| Maker | Nous Research | Verified Oct 14, 2026 |
| License | Llama Community License | Verified Oct 14, 2026 |
| License plain | Meta's own license. You can download and use it for free, but Meta sets the rules. The Open Source Initiative says it is not open source. | Verified Oct 14, 2026 |
| Truly open | No, open weights with custom rules | Verified Oct 14, 2026 |
| Business use | Yes for most businesses. If your products had over 700 million monthly users, you need a separate deal with Meta. You must follow Meta's use policy and show "Built with Llama" if you share it. | Verified Oct 14, 2026 |
| Signup needed | No. Download without an account. | Verified Oct 14, 2026 |
| Parameters | 8.0 billion | Verified Oct 14, 2026 |
| Open training data | Not yet checked | We have not found a full public training data release. Not yet checked in depth. |
| Context window | 128K tokens | Verified Oct 14, 2026 |
| First posted | 2024-07-28 | Verified Oct 14, 2026 |
| Gguf files | NousResearch/Hermes-3-Llama-3.1-8B-GGUF | Verified Oct 14, 2026 |
| Hermes ok | Yes | Verified Oct 14, 2026 |
If the maker's page and this page disagree, trust the maker. Tell us what we got wrong.
Newsletter
Which new models are worth your time, which ones are just hype, and the license gotchas before they bite. All the useful bits, none of the nerd-party small talk.
This opens our sign-up page on Beehiiv, our email provider. Confirm your email there to join.