Qwen3 Reranker 0.6B Seq Cls vLLM W8A8
JSON →A quantized 0.6B parameter reranker based on Qwen3, using sequence classification with W8A8 quantization for vLLM.
Specs
context window 32K tokens
max output 32K tokens
Capabilities
streaming
A quantized 0.6B parameter reranker based on Qwen3, using sequence classification with W8A8 quantization for vLLM.