arcflare_
Embedding475M official

nomic-embed-text-v2-moe

by Nomic AI

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

#embedding#small
arcflare pull nomic-ai/nomic-embed-text-v2-moe-GGUF:Q8_0

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

nomic-embed-text-v2-moe

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

Get it

arcflare pull nomic-ai/nomic-embed-text-v2-moe-GGUF:Q8_0
arcflare run nomic-embed-text-v2-moe

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 Q8_0 file by default: 0.51 GB. Also published: Q4_K_M (0.34 GB), Q6_K (0.4 GB), f16 (0.96 GB)
  • Trained for a 512 context
  • Licence: Apache-2.0. Read it before commercial use

Sizes

  • 475m · 0.51GB

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

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

bge-m3

BAAI

Embedding

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

size
568M
vram
~2 GB
license
MIT

8% of a 24 GB card

#embedding #small