← All models

Alibaba gte-Qwen2-7B-instruct

Alibaba

open_source

Capabilities

Long ContextMultilingual

Strengths

  • Top-tier open MTEB performance — competitive with hosted flagships
  • Long 32k context
  • Multilingual
  • Apache 2.0 licence

Weaknesses

  • Heavy — 7B params, 8 GB VRAM at Q8
  • Slower than smaller open models

Pricing

Input / 1M tokens

Free (self-host)

Output

Hosting

Open weights

Embedding specs

Output dimension

3584

Max input

32,000 tokens

Matryoshka

No

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
80%

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.