jina-reranker-m0
--- pipelinetag: text-classification tags: - sentence-transformers - vidore - reranker - qwen2vl language: - multilingual basemodel: - Qwen/Qwen2-VL-2B-Instruct inference: false license: cc-by-nc-4.0 libraryname: transformers ---
Params
2.4 B
Context
32,768
Downloads 30d
396 K
Likes
120
Download history
daily snapshots · 19 days396 K273 K
Sep 2Sep 8Sep 14Sep 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 | 4.9 GB | 6.2 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 32K ctx | 4.9 GB | 7.3 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
- JinaVLForRanking
- Parameters
- 2.4 B
- Tensor type
- BF16
- Context length
- 32,768
- Vocabulary
- 151,936
- Layers / heads
- 28 / 12
- Licence
- cc-by-nc-4.0
- First seen on the Hub
- 2025-03-27
- Base model
- Qwen2-VL-2B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-02
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-classification model