Qwen3 VL Reranker 2B needs about 3.3 GB of memory at Q8_0 (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.8 GB (Q8_0) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Qwen3‑VL‑Reranker‑2B: multimodal text‑image relevance scoring
Qwen3‑VL‑Reranker‑2B is a 1.72 billion‑parameter model designed for cross‑modal retrieval. It accepts text, images, or mixed inputs and outputs a relevance probability. The model is available in GGUF format for llama.cpp.
Good at
- Multimodal reranking
- Text‑image relevance scoring
- Cross‑modal retrieval
Limits
- No vision support in llama.cpp stock endpoint
- Requires --reranking and --pooling rank
- Large VRAM for full precision
Best for
- Refining search results
- Evaluating image‑text pairs
- Ranking multimodal documents
Who it’s for. Developers building multimodal search pipelines who need a lightweight reranker. The model supports over 30 languages and can be integrated with existing embedding models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use the Q8_0 quant (1.83 GB file, ~3.3 GB memory at 8k context). For 16 GB VRAM the F16 quant (3.45 GB file, ~4.9 GB memory at 8k context) offers higher precision.
What GPU do you need for Qwen3 VL Reranker 2B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).
Which Qwen3 VL Reranker 2B quant should you choose?
Q8_0 (1.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3 VL Reranker 2B
How much VRAM does Qwen3 VL Reranker 2B need?
About 3.3 GB at Q8_0 with an 8K context window. That is the 1.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen3 VL Reranker 2B on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 VL Reranker 2B GGUF?
It depends on the quant: Q8_0 is 1.8 GB, F16 is 3.4 GB.
What context length does Qwen3 VL Reranker 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Qwen3 VL Reranker 2B GGUF?
The files are on Hugging Face in the bealore/Qwen3-VL-Reranker-2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3 VL Reranker 2B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Qwen3‑VL‑Reranker‑2B on 8 GB VRAM?
Yes, the Q8_0 quant uses about 3.3 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support image inputs in llama.cpp?
Image support requires the mmproj file and the --pooling rank flag; the stock llama.cpp endpoint is text‑only.
What license applies to this model?
The model is released under the apache‑2.0 license.