Octen/Octen-Embedding-0.6B download history
Octen/Octen-Embedding-0.6B is a 596M-parameter sentence similarity model by Octen. In the last 30 days it was downloaded 22,969 times (5,752 in the last 7 days), and 195,405 times in total.
It ranks #5,418 on the Hub by monthly downloads and #201 among sentence similarity models.
It has 52 likes, 1 of them in the last week.
It is a fine-tune of Qwen/Qwen3-Embedding-0.6B.
14 models build on Octen-Embedding-0.6B: 12 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 26,884 times in the last 30 days. See the Octen-Embedding-0.6B galaxy.
Most downloaded derivatives
- mradermacher/Octen-Embedding-0.6B-i1-GGUF (quantized), 799 downloads in 30 days
- ENOSYS/Octen-Embedding-0.6B-750-v1-GGUF (quantized), 748 downloads in 30 days
- mradermacher/Octen-Embedding-0.6B-GGUF (quantized), 556 downloads in 30 days
- cstr/octen-0.6b-GGUF (quantized), 266 downloads in 30 days
- litillabs/litil-embed-0.6b (finetune), 169 downloads in 30 days
- cstr/octen-embedding-0.6b-onnx-int4 (quantized), 138 downloads in 30 days
- cstr/Octen-Embedding-0.6B-ONNX-INT8-FULL (quantized), 133 downloads in 30 days
- cstr/Octen-Embedding-0.6B-ONNX (quantized), 124 downloads in 30 days
- rsl-ai/octen-embedding-0.6-finetuned (finetune), 124 downloads in 30 days
- mykor/Octen-Embedding-0.6B-GGUF (quantized), 105 downloads in 30 days
- cstr/Octen-Embedding-0.6B-GGUF (quantized), 86 downloads in 30 days
- cstr/Octen-Embedding-0.6B-ONNX-INT8 (quantized), 17 downloads in 30 days