Skip to content

LFM2.5-ColBERT-350M-4bit

mlx-community/LFM2.5-ColBERT-350M-4bit
4-bit Open on Hugging Face
Parameters
353M
Weights (est.)
≈ 199 MB
Mac memory (est.)
8 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
LiquidAI/LFM2.5-ColBERT-350M (finetune)
Vendor
LiquidAI
Task
Sentence similarity
Quantisation
4-bit
Licence
lfm1.0
Downloads
19 in the last 30 days · 290 all time · 1 likes
Published
2026-06-22 · updated 2026-06-22 (4mo ago)
Languages
en, es, de, fr, it, pt, ar, sv, no, ja, ko
Tags
lfm2, lfm2.5, ColBERT, late-interaction, feature-extraction, retrieval, quantized, custom_code

Other MLX builds of LiquidAI/LFM2.5-ColBERT-350M

Build Quantisation Weights Mac memory Downloads
LFM2.5-ColBERT-350M-4bit (this one) 4-bit ≈ 199 MB 8 GB+ 19
LFM2.5-ColBERT-350M-8bit 8-bit ≈ 376 MB 8 GB+ 22
LFM2.5-ColBERT-350M-bf16 bf16 ≈ 707 MB 8 GB+ 10