Qwen3-Embedding-0.6B
A text embedding model released by Alibaba's Tongyi Qianwen team, licensed under Apache 2.0. It supports a 32K token context and 1024-dimensional vectors, and is suited for local deployment on GPUs.
Timeline (last 90 days)
Yalda Embedding is a Persian retrieval model with 595.8 million parameters, fine-tuned from Qwen3-Embedding-0.6B and trained on more than one million query-document pairs.
Yalda Embedding surpasses Qwen3-Embedding-0.6B and F2LLM-v2-0.6B on every task.
Qwen3-Embedding-0.6B uses the Apache 2.0 license, supports a 32K token context and 1024-dimensional vectors, and in testing peaked at only 2.49 GiB of VRAM.
All Facts (3)
Yalda Embedding is a Persian retrieval model with 595.8 million parameters, fine-tuned from Qwen3-Embedding-0.6B and trained on more than one million query-document pairs.
50%UnverifiedYalda Embedding surpasses Qwen3-Embedding-0.6B and F2LLM-v2-0.6B on every task.
50%UnverifiedQwen3-Embedding-0.6B uses the Apache 2.0 license, supports a 32K token context and 1024-dimensional vectors, and in testing peaked at only 2.49 GiB of VRAM.
50%