gte-Qwen2-1.5B-instruct
gte-Qwen2-1.5B-instruct is the latest model in the gte (General Text Embedding) model family. The model is built on Qwen2-1.5B LLM model and use the same training data and strategies as the gte-Qwen2-7B-instruct model.
Params
1.8 B
Context
131,072
Downloads 30d
1.2 M
Likes
236
Download history
daily snapshots · 10 days1.2 M1.1 M
Jul 28Jul 31Aug 3Aug 6
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 7.1 GB | 8.6 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 7.1 GB | 12.6 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen2ForCausalLM
- Parameters
- 1.8 B
- Tensor type
- F32
- Context length
- 131,072
- Vocabulary
- 151,646
- Layers / heads
- 28 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2024-06-29
- Training datasets
- undisclosed
- MTEB ArguAna (reported)
- 84.851
- MTEB BIOSSES (reported)
- 80.574125092726
- MTEB ArxivClusteringP2P (reported)
- 50.511868162026
- MTEB ArxivClusteringS2S (reported)
- 45.007803189284
- MTEB BiorxivClusteringP2P (reported)
- 43.207546089349
- MTEB BiorxivClusteringS2S (reported)
- 38.818037697336
- MTEB AskUbuntuDupQuestions (reported)
- 77.661588180979
- MTEB Banking77Classification (reported)
- 87.253073224433
- MTEB CQADupstackAndroidRetrieval (reported)
- 35.423
- MTEB AmazonPolarityClassification (reported)
- 96.609425969406
- MTEB AmazonReviewsClassification (en) (reported)
- 54.905534802949
- MTEB AmazonCounterfactualClassification (en) (reported)
- 78.504165990512
- Added to our catalog
- 2026-07-28
Compare with
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.