Model reference · open weights

LFM2-ColBERT

LFM2-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.

Licence fee required Embeddings LiquidAI 1 variants 25k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What LFM2-ColBERT is

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-ColBERT-350M LFM2-ColBERT-350M is a late interaction retriever with excellent multilingual performance. It allows you to store documents in one language (for example, a product description in English) and retrieve them in many languages with high accuracy. - LFM2-ColBERT-350M offers best-in-class accuracy across different languages. - Inference speed is on par with models 2.3 times smaller, thanks to the efficient LFM2 backbone. - You can use it as a drop-in replacement in your current RAG pipelines to improve performance. Find more information about LFM2-ColBERT-350M in our blog post. [!NOTE] 🚀 Try our demo: https://huggingface.co/spaces/LiquidAI/LFM2-ColBERT 📄 Model details Late interaction retrievers like LFM2-ColBERT-350M are particularly interesting because they preserve much of the expressivity of re-rankers while retaining the efficiency of bi-encoders. In practice, they're used to both retrieve documents at scale (like bi-encoders) and rank them at the same time (like rerankers). We recommend using this model for various RAG use cases, such as: - E-commerce: Find products across many languages with semantic search at scale. - On-device semantic search: Ask questions to your phone in natural language to retrieve files, emails, and notes. - Enterprise knowledge assistants: Retrieve internal legal, financial, and technical documents in different languages. Document length: 512 tokens Query length: 32 tokens Output dimensionality: 128 tokens Similarity function: MaxSim Supported languages: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish. 🏃 How to run Sentence Transformers This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the MultiVectorEncoder: PyLate First, install the PyLate and transformers library: Retrieval Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity searc

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerLiquidAI
TypeEmbedding models
Parameters (lead)353M
Context125k tokens
Variants1
Runs withPyLate
Released2025-10-28
Popularity25k downloads / month
Likes152
LicenceCommercial licence needed

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
LFM2-ColBERT-350M353MBF16~0.8 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@10.4
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@30.52
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@50.64
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@100.8
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@10.4
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@30.207
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@50.156
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@100.118
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@10.195
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@30.273
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@50.316
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@100.459
Py Late Information RetrievalNanoClimateFEVERMaxsim Ndcg@100.387
Py Late Information RetrievalNanoClimateFEVERMaxsim Mrr@100.506
Py Late Information RetrievalNanoClimateFEVERMaxsim Map@1000.313
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@10.86
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@30.92
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@50.94
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@100.98
Py Late Information RetrievalNanoDBPediaMaxsim Precision@10.86
Py Late Information RetrievalNanoDBPediaMaxsim Precision@30.7
Py Late Information RetrievalNanoDBPediaMaxsim Precision@50.64
Py Late Information RetrievalNanoDBPediaMaxsim Precision@100.566
Py Late Information RetrievalNanoDBPediaMaxsim Recall@10.121

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys lfm2-colbert for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-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-colbert","input":"text to embed"}'

Details

Languages, data & research

Languages

en ar zh fr de ja ko es

Tags

PyLate safetensors lfm2 liquid edge ColBERT multi-vector sentence-transformers sentence-similarity feature-extraction en ar zh fr

Papers

Licence

Commercial licence needed

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 ↗

Sources

Weights & code

Want LFM2-ColBERT on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms