{"slug":"boboliu/Qwen3-Embedding-4B-W4A16-G128","title":"Qwen3 Embedding 4B W4A16 G128","description":"A 4-bit quantized embedding model based on Qwen3 with 4B parameters, using W4A16 and group size 128 for efficient retrieval.","provider":"boboliu","model_type":"embedding","status":"active","context_window":40960,"max_output_tokens":40960,"pricing":{"currency":"USD","input_per_mtok":null,"output_per_mtok":null},"modalities":["text"],"capabilities":["fine-tunable"],"knowledge_cutoff":null,"release_date":"2025-04-01T00:00:00.000Z","deprecation_date":null,"retirement_date":null,"aliases":[],"homepage":"https://huggingface.co/boboliu/Qwen3-Embedding-4B-W4A16-G128","docs":null,"categories":["ai-ml"],"tags":[],"last_verified":"2026-06-09T00:00:00.000Z","next_check":"2026-09-07T00:00:00.000Z","created_at":"2026-06-09T18:15:00.339Z","updated_at":"2026-06-09T18:15:00.339Z"}