Qwen3-Reranker-4B-AWQ-INT4
INT4 weight-only quantization of Qwen/Qwen3-Reranker-4B.
Qwen 3 Reranker 4B in INT4. Pair with the Embedding kit for a fully local retrieval stack.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3-Reranker-4B |
| Quantization | INT4 weight-only |
| Approx. on-disk size | ~2.7 GB |
| Languages | English |
Load (vLLM)
vllm serve drawais/Qwen3-Reranker-4B-AWQ-INT4 \
--max-model-len 32768 \
--gpu-memory-utilization 0.94
from vllm import LLM, SamplingParams
llm = LLM(model="drawais/Qwen3-Reranker-4B-AWQ-INT4", max_model_len=32768)
print(llm.generate(["Hello!"], SamplingParams(max_tokens=128))[0].outputs[0].text)
Footprint
~2.7 GB on disk. Recommended VRAM: enough headroom for KV cache.
License & attribution
This artifact is a derivative work of Qwen/Qwen3-Reranker-4B,
released by its original authors under the Apache License, Version 2.0.
This artifact is distributed under the same license. The full license text is
included in LICENSE, and required attribution is in NOTICE.
License text: https://www.apache.org/licenses/LICENSE-2.0 Source model: https://huggingface.co/Qwen/Qwen3-Reranker-4B