O

Octen Embedding 8B

Dec 2025
OOcten Embedding 8B
Compare in
on
self-host onlyprice
61.4RTEB French beta
Dec 2025released
4,096Dimensions
41K tokensMax input
en, zhLanguages

Alternatives?

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval

FAQ

How much does Octen Embedding 8B cost?›

There is no per-unit API price: self-host only.

Is Octen Embedding 8B free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Octen Embedding 8B, and what is it best at?›

#6 of 212 in Embeddings.

Is Octen Embedding 8B better than Qwen 3 Embedding 4B?›

On MTEB Thai v1 · Pair Classification · Thai, Octen Embedding 8B scores 85.7 vs 86.7 — about the same.

When was Octen Embedding 8B released? Is there a newer version?›

Released 2025-12-23. It is the current version in its line.

Is Octen Embedding 8B open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Octen Embedding 8B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Octen Embedding 8B?›

Octen Embedding 8B is an open-weights embeddings & retrieval model from Octen, released Dec 2025.

What are the best alternatives to Octen Embedding 8B?›

Qwen 3 Embedding 8B (better).