a

Giga Embeddings Instruct

Sep 2025
aGiga Embeddings Instruct
Compare in
on
self-host onlyprice
59.7MTEB English v2
Sep 2025released
2,048Dimensions
4K tokensMax input
en, ruLanguages

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use

FAQ

How much does Giga Embeddings Instruct cost?›

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

Is Giga Embeddings Instruct free to use?›

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

How good is Giga Embeddings Instruct, and what is it best at?›

#24 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.

Is Giga Embeddings Instruct better than F2LLM 1.7B?›

On MTEB English v2 · Classification · English, Giga Embeddings Instruct scores 90.8 vs 90.9 — about the same.

When was Giga Embeddings Instruct released? Is there a newer version?›

Released 2025-09-23. It is the current version in its line.

Is Giga Embeddings Instruct open source?›

Yes, the weights are open (MIT licence).

Can I run Giga Embeddings Instruct locally?›

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

What is Giga Embeddings Instruct?›

Giga Embeddings Instruct is an open-weights embeddings & retrieval model from ai-sage, released Sep 2025.

What are the best alternatives to Giga Embeddings Instruct?›

Voyage 3 M Exp (better), F2LLM 4B (open weights).