Model reference · open weights
gte-large-onnx is an open-weight embedding model from Qdrant.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the Qdrant/gte-large-onnx model card, 2026-10-01
What it is
| Released by | Qdrant |
|---|---|
| Released | 2024-01-16 |
From the model card
ONNX port of thenlper/gte-large for text classification and similarity searches.
Here's an example of performing inference using the model with FastEmbed.
from fastembed import TextEmbedding
documents = [
"You should stay, study and sprint.",
"History can only prepare us to be surprised yet again.",
]
model = TextEmbedding(model_name="thenlper/gte-large")
embeddings = list(model.embed(documents))
# [
# array([
# 0.00611658, 0.00068912, -0.0203846, ..., -0.01751488, -0.01174267,
# 0.01463472
# ],
# dtype=float32),
# array([
# 0.00173448, -0.00329958, 0.01557874, ..., -0.01473586, 0.0281806,
# -0.00448205
# ],
# dtype=float32)
# ]
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.