v2.3 · 2026-08-09

LFM2.5 ColBERT 350M

lfm2-5-colbert-350m

EMBEDDING

LFM2.5 ColBERT 350M is a 0.353B embedding model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

Liquid AI

FAMILY

LFM2.5

MODEL TYPE

embedding

PARAMETERS

0.353B

MODALITIES

text

ARCHITECTURE

Bidirectional late-interaction retriever with per-token vectors and MaxSim scoring

CONTEXT WINDOW

512 tokens

TRAINING TOKENS

—

RELEASE DATE

2026-06-18

LICENSE & LINKS

LFM Open License v1.0license text

MODEL CARD

huggingface.co/LiquidAI/LFM2.5-ColBERT-350M

HUGGING FACE

LiquidAI/LFM2.5-ColBERT-350M

GGUF REPOSITORIES

LiquidAI/LFM2.5-ColBERT-350M-GGUF official

Official GGUF repository for llama.cpp-compatible late-interaction retrieval.

SETUP HINTS

LLAMA.CPP

Use the official GGUF repository with current reranking support.

RAM / VRAM ESTIMATES

MIN RAM

4 GB

COMFORTABLE RAM

8 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

yes

8 GB RAM

comfortable

16 GB RAM

comfortable

32 GB RAM

comfortable

8 GB VRAM

not required

12 GB VRAM

not required

24 GB VRAM

not required

Apple Silicon (unified memory)

comfortable

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·Multilingual retrieval where higher accuracy matters more than index size.

AVOID IF

·You need the smallest possible index or a simple single-vector embedding pipeline.

CAVEATS

·Per-token vectors create a larger index than the companion embedding model.

·The 512-token document limit requires chunking longer material.

·Vendor benchmark and latency figures have not been reproduced by LocalLLMGuide.com.

·The custom license includes a commercial-use revenue threshold.

SOURCE URLS

[source 1] [source 2] [source 3]

FIELD EVIDENCE