Qwen3-VL-Embedding-2B
The Qwen3-VL-Embedding and Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities.
Params
2.1 B
Context
—
Downloads 30d
1.2 M
Likes
455
Download history
daily snapshots · 55 days
▲ 32 K in the last 30 days (2.6%)
1.4 M1.2 M
Aug 22Sep 1Sep 11Sep 20
1.4 M963 K
Jul 28Aug 15Sep 2Sep 20
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 | bf16 | 4.3 GB | 5.5 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
- Qwen3VLForConditionalGeneration
- Parameters
- 2.1 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-01-07
- Base model
- Qwen3-VL-2B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any sentence-similarity model