arcflare_
Embedding0.6B official

qwen3-embedding

by Alibaba Qwen

Qwen3-Embedding: multilingual text and code embeddings at 0.6B, 4B and 8B, near the top of the MTEB leaderboard.

#embedding#retrieval#multilingual#rag
arcflare pull Qwen/Qwen3-Embedding-0.6B-GGUF:Q8_0

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

qwen3-embedding

Qwen3-Embedding: multilingual text and code embeddings at 0.6B, 4B and 8B, near the top of the MTEB leaderboard.

Get it

arcflare pull Qwen/Qwen3-Embedding-0.6B-GGUF:Q8_0
arcflare run qwen3-embedding-0.6b

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

  • Served at /v1/embeddings by arcflare serve
  • Instruction-aware: tell it what the query is for
  • 32K input length

Sizes

  • 0.6b · 0.6GB
  • 4b · 4.3GB
  • 8b · 8.1GB

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

[ 03 ] // relatedmore →

mxbai-embed-large

Mixedbread AI

Embedding

A state-of-the-art large embedding model for English retrieval and semantic search.

size
335M
vram
~2 GB
license
Apache-2.0

8% of a 24 GB card

#embedding #rag #search

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