Skip to content
AETRONConstructor
My neuronetsRegistrySpacesDocsFAQ
Sign in
AETRON

A constructor for AI services on AETRON’s decentralised network of GPU miners.

ProductCreate a neuronetModel catalogueDatasetsSpacesMy payouts
ResourcesDocumentationAPITimings & statusesFAQ
Networkaetron.ioPrivacy & verification
© 2026 AETRONTestnet
Models/embeddinggemma-300m
G

EmbeddingGemma-300m

Google · Gemma
Create a neuronet with this model →
EmbeddingGemma-TermsgatedTrusted300M params
embeddingon-device

On-device embeddings, 100+ languages.

On-device embeddings, 100+ languages.

At a glance

  • Task: Embedding (EmbeddingV1)
  • Params: 300M
  • License: Gemma-Terms (commercial use OK)
  • Hardware: 1 GB+ VRAM
  • dtype: Bf16, Fp16
Create a neuronet with this model →
Overview
Task
Embedding · EmbeddingV1
Family
Gemma
Tier
Trusted
Status
active
Runtime spec
dtype
Bf16
attention
FlashAttn2
compile
ReduceOverhead
seed
0
gpu_arch
Sm89
Runs on
Consumer, Datacenter
Hardware
Min VRAM
1 GB
Recommended
2 GB
Tensor parallel
≥1
TEE archs
Sm89, Sm90
Verification defaults
Tier
B
Trust
Level1
Security
Standard
Privacy
P0
Min pulse score
100
License
spdx
Gemma-Terms ↗
Commercial use
✓
Redistribution
✓
Source & provenance
Repo
google/embeddinggemma-300m ↗
Revision
57c266a740
Added
2026-06-08
Verified
2026-06-08