H

Speed Embedding 7B Instruct

Oct 2024
HSpeed Embedding 7B Instruct
Compare in
on
self-host onlyprice
39.1MTEB English v2
Oct 2024released
4,096Dimensions
33K tokensMax input
enLanguages

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
LicenceMITfree for commercial use

Benchmarks

in Embeddings & Retrieval

FAQ

How much does Speed Embedding 7B Instruct cost?›

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

Is Speed Embedding 7B Instruct free to use?›

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

How good is Speed Embedding 7B Instruct, and what is it best at?›

#151 of 200 in Embeddings.

Is Speed Embedding 7B Instruct better than Hinvec?›

On MTEB Indic v1 · Classification · multilingual (8 languages), Speed Embedding 7B Instruct scores 55.8 vs 57.1 — lower.

When was Speed Embedding 7B Instruct released? Is there a newer version?›

Released 2024-10-31. It is the current version in its line.

Is Speed Embedding 7B Instruct open source?›

Yes, the weights are open (MIT licence).

Can I run Speed Embedding 7B Instruct locally?›

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

What is Speed Embedding 7B Instruct?›

Speed Embedding 7B Instruct is an open-weights embeddings & retrieval model from Haon-Chen, released Oct 2024.

What are the best alternatives to Speed Embedding 7B Instruct?›

Multilingual E5 Large Instruct (better), F2LLM v2 14B (open weights).