Qwen3-Reranker-4B needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.5 GB (Q4_K_M) to 2.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qwen3-Reranker-4B: 4.02B parameter dense model for embeddings and reasoning
Qwen3-Reranker-4B is a 4.02B parameter dense model derived from Qwen3-4B-Base. It supports embedding, reasoning, and tool usage. The model is trained on 40960 token context and released under apache-2.0.
Good at
- Embedding generation
- Reasoning tasks
- Tool integration
Limits
- No vision support
- Context limited to 40960 tokens
- Requires 4.2–4.6 GB VRAM at 8k context
Best for
- Search engine ranking
- Semantic similarity matching
- Chatbot back‑end
Who it’s for. Developers building retrieval‑augmented systems or semantic search pipelines. The model is suitable for applications needing high‑quality embeddings and reasoning within a 4 B parameter budget.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_M | 2.9 GB | 4.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (2.48 GB file, ~4.2 GB VRAM at 8k context). If 10 GB VRAM is available, Q5_K_M (2.9 GB file, ~4.6 GB VRAM) offers slightly higher precision. Both quants are approximate memory estimates.
What GPU do you need for Qwen3-Reranker-4B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q5_K_M (2.9 GB file, about 4.6 GB in use).
Which Qwen3-Reranker-4B quant should you choose?
Q4_K_M is the usual starting point for Qwen3-Reranker-4B: it balances file size and quality well. Here it is a 2.5 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3-Reranker-4B
How much VRAM does Qwen3-Reranker-4B need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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-Reranker-4B on an 8 GB GPU?
Yes, with Q5_K_M: the 2.9 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3-Reranker-4B GGUF?
It depends on the quant: Q4_K_M is 2.5 GB, Q5_K_M is 2.9 GB.
What context length does Qwen3-Reranker-4B support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Qwen3-Reranker-4B GGUF?
The files are on Hugging Face in the dengcao/Qwen3-Reranker-4B-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-Reranker-4B 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-Reranker-4B on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 4.2 GB VRAM at 8k context, which fits within 8 GB. The Q5_K_M quant needs about 4.6 GB VRAM, also within 8 GB.
What license applies to this model?
The model is released under the apache-2.0 license, allowing commercial use and modification.
Does the model support vision tasks?
No, the model does not include vision capabilities.