Qwen3 Embedding 8B NVFP4 This is a quantized version of Qwen/Qwen3 Embedding 8B using NVFP4 (NVIDIA FP4) quantization via llmcompressor. Quantization Details The model was quantized using the following script: Quantization scheme : NVFP4 (all Linear layers) Calibration : 100 samples from CohereLabs/aya dataset (Greek subset), max sequence length 4096 Framework : llmcompressor with compressed tensors Usage with vLLM Original Model Card: Qwen3 Embedding 8B Highlights The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility : The embedding model has achieved state…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy