Qwen3-8B-DSpine-b16: 4GB+ VRAM
Discover DSpine, a parallel draft model by Tencent for speculative decoding that enhances inference speed and accepta ...
News, quick references and our own measurements for open-weight models you can run locally
Discover DSpine, a parallel draft model by Tencent for speculative decoding that enhances inference speed and accepta ...