Granite 3.3 2B
Tiny business helper. About 4 GB, which is basically nothing.
Short answer (as of Oct 14, 2026): LFM2 1.2B is a local AI model from Liquid AI. Truly open? No, open weights with custom rules. Business use: yes, with limits. Our estimate says it needs about 3 GB of RAM. Trust score 64 of 100.
As of Oct 14, 2026: license LFM Open License v1.0; business use yes, with limits; sign-up not needed; about 3 GB RAM (estimate); trust score 64/100. Sources.
Very small model for old laptops and phones.
In non-nerd speak
Who makes it: Liquid AI. The files come from the maker's own Hugging Face account.
License: LFM Open License v1.0. Liquid AI's own license. It is free for business use only while your company makes under 10 million US dollars a year.
Business use: Only if your company makes under 10 million US dollars a year. Bigger companies need a deal with Liquid AI.
Training data: We have not found a full public data release. Not yet checked in depth.
Will it run on my computer?
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.
How to run it in LM Studio
- Get LM Studio from lmstudio.ai and open it.
- Open the Discover tab. Search for
LiquidAI/LFM2-1.2B-GGUF. - Pick a file that ends in
Q4_K_M. It is the best mix of size and quality for most people. - Click Download. When it is done, open a new chat and load the model.
The files are GGUF builds that LM Studio can load. We checked that this repo exists on Oct 14, 2026. Full LM Studio guide.
How to use it with Hermes
Does it fit? Yes. Its memory window is big enough for Hermes.
- Load the model in LM Studio. Set the context length to at least 64000.
- In LM Studio, open the Developer tab and start the server.
- In a terminal, run
hermes model. Choose LM Studio and press Enter to keephttp://localhost:1234/v1. - Pick this model from the list. Then run
hermesto start.
Common questions
Is LFM2 1.2B truly open source?
No, open weights with custom rules. Liquid AI's own license. It is free for business use only while your company makes under 10 million US dollars a year.
Can I use LFM2 1.2B for my business?
Only if your company makes under 10 million US dollars a year. Bigger companies need a deal with Liquid AI.
Do I need to sign up to download LFM2 1.2B?
No. Download without an account.
How much memory does LFM2 1.2B need?
Our estimate is about 3 GB of RAM for a 4-bit file of about 0.7 GB. This is a rough guide, not a test.
Sources we checked
| Fact | What we found | Status |
|---|---|---|
| Maker | Liquid AI | Verified Oct 14, 2026 |
| License | LFM Open License v1.0 | Verified Oct 14, 2026 |
| License plain | Liquid AI's own license. It is free for business use only while your company makes under 10 million US dollars a year. | Verified Oct 14, 2026 |
| Truly open | No, open weights with custom rules | Verified Oct 14, 2026 |
| Business use | Only if your company makes under 10 million US dollars a year. Bigger companies need a deal with Liquid AI. | Verified Oct 14, 2026 |
| Signup needed | No. Download without an account. | Verified Oct 14, 2026 |
| Parameters | 1.2 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 | 125K tokens | Verified Oct 14, 2026 |
| First posted | 2025-07-10 | Verified Oct 14, 2026 |
| Gguf files | LiquidAI/LFM2-1.2B-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
Local AI news for non-coders
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.