Embedding568M official

bge-m3

by BAAI

Multi-functionality, multilingual (100+ languages) and multi-granularity embedding model handling inputs up to 8192 tokens.

#embedding #small

arcflare pull ggml-org/bge-m3-Q8_0-GGUF

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

bge-m3

Multi-functionality, multilingual (100+ languages) and multi-granularity embedding model handling inputs up to 8192 tokens.

Get it

arcflare pull ggml-org/bge-m3-Q8_0-GGUF

arcflare run bge-m3-q8_0

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

Downloads the single file by default: 0.63 GB
Trained for a 8K context
Licence: MIT. Read it before commercial use

Sizes

568m · 0.63GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

nomic-embed-text

Nomic AI

Embedding

English text embedding model with Matryoshka representation learning for resizable embeddings; requires task instruction prefixes.

size: 137M
vram: ~2 GB
license: Apache-2.0

8% of a 24 GB card

#embedding #small

nomic-embed-text-v2-moe

Nomic AI

Embedding

Multilingual mixture-of-experts text embedding model (475M total, 305M active) supporting about 100 languages with Matryoshka embeddings.

size: 475M
vram: ~2 GB
license: Apache-2.0

8% of a 24 GB card

#embedding #small

embeddinggemma-300m

Google

Embedding

300M-parameter open embedding model from Google, built from Gemma 3 and trained on 100+ languages; 768-dim output with Matryoshka truncation.

size: 300M
vram: ~2 GB
license: Gemma

8% of a 24 GB card

#embedding #small