Model reference · open weights
LFM2-RAG is an open-weight language model from LiquidAI. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | LiquidAI |
|---|---|
| Type | Language models |
| Task | Text gen |
| Runs with | transformers |
| Based on | LiquidAI/LFM2-1.2B-RAG |
| Released | 2025-09-05 |
| Popularity | 2k downloads / month |
| Licence | Commercial licence needed |
About
src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" />
Based on LFM2-1.2B, LFM2-1.2B-RAG is specialized in answering questions based on provided contextual documents, for use in RAG (Retrieval-Augmented Generation) systems.
Use cases:
You can find more information about other task-specific models in this blog post.
Example usage with llama.cpp:
llama-cli -hf LiquidAI/LFM2-1.2B-RAG-GGUF
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys lfm2-rag for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-rag below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"lfm2-rag","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.