← All models

Nomic nomic-embed-text-v2-moe

Nomic AI

open_source

Capabilities

Strengths

  • Top open English MTEB scores at the 1B-param scale
  • Matryoshka — 64 to 768 dim
  • Apache 2.0 licence
  • Mixture-of-experts — efficient inference

Weaknesses

  • 2k input limit
  • English-leaning vs BGE-M3

Pricing

Input / 1M tokens

Free (self-host)

Output

Hosting

Open weights

Embedding specs

Output dimension

768

Max input

2,048 tokens

Matryoshka

Supported

Matryoshka representation learning: dimension can be truncated to a smaller size at index time without retraining, trading retrieval quality for index size and speed.

Transparency

Open weights

10.0 / 10

Open training data

5.0 / 10

Open methodology

7.0 / 10

Licence openness

9.0 / 10

Provider disclosure

7.0 / 10

FMTI company score

N/A

Composite:7.5 / 10

Open weights with permissive licence; methodology partially documented.

Sustainability

Inference energy

8.5 / 10

Training footprint

N/A

Provider infrastructure

7.0 / 10

Composite:7.8 / 10

Small enough to run on local hardware — user controls the energy source.

MTEB quality

Embedding
73%

Grounded in the MTEB (Massive Text Embedding Benchmark) Overall average published by the model authors. Bearing collapses MTEB's retrieval, STS, classification, and clustering categories into a single quality signal because they correlate strongly for embedding models. Methodology.