Model reference · open weights
LFM2.5-ColBERT is an open-weight embedding model from LiquidAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
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;" / LFM2.5-ColBERT-350M We release two new best-in-class multilingual retrieval models: - LFM2.5-Embedding-350M — A dense bi-encoder, one vector per document. Smallest, fastest index. - LFM2.5-ColBERT-350M — A late-interaction model. One vector per token, matched via MaxSim. Higher accuracy and better generalization at the cost of index size. Both models are 350M params and the first bidirectional members of the LFM family, built on LFM2.5-350M-Base. They can be used as a drop-in replacement for your current RAG pipeline and target fast, cheap, and reliable multilingual / cross-lingual search across 11 languages. Find more details about the bidirectional architecture and training recipe in our blog post. [!NOTE] 💻 Demo: https://huggingface.co/spaces/LiquidAI/colbert-tool-selection 📄 Model details Document length: 512 tokens Query length: 32 tokens Supported languages: English, Spanish, German, French, Italian, Portuguese, Arabic, Swedish, Norwegian, Japanese, Korean. Architecture: We recommend LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M for short-context retrieval use cases, such as: - E-commerce: find products across many languages with semantic search at scale. - FAQ and support knowledge bases: retrieve the right answer reliably across customer-facing surfaces. - On-device semantic search: search files, emails, and notes locally on consumer hardware. - Enterprise knowledge assistants: retrieve internal legal, financial, and technical documents across languages. 🏃 How to run Using Sentence Transformers This model can be used as a multi-vector (ColBERT-style late interaction) retriever directly with Sentence Transformers via the MultiVectorEncoder. Using PyLate Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity search. First, install PyLate and transformers: Indexing documents Load LFM2.5-ColBERT-350M and initialize the PLAID index, then encode and ind
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | LiquidAI |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 353M |
| Context | 125k tokens |
| Variants | 1 |
| Runs with | PyLate |
| Based on | LiquidAI/LFM2.5-350M-Base |
| Released | 2026-05-20 |
| Popularity | 4k downloads / month |
| Likes | 117 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| LFM2.5-ColBERT-350M | 353M | BF16 | ~0.8 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys lfm2-5-colbert for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-5-colbert below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"lfm2-5-colbert","input":"text to embed"}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore