New Models

Qwen3.8-27B-DSpine-b16 Draft Model for Speculative Decoding: 8GB+ VRAM

Explore tencent/Qwen3.8-27B-DSpine-b16, a draft model for speculative decoding using the DSpine method to accelerate ...

New Models

Ling-3.0-tiny-UBTree Draft Model for Speculative Decoding: 4GB+ VRAM

Learn about inclusionAI/Ling-3.0-tiny-UBTree, a draft model for speculative decoding designed to accelerate the Ling- ...

New Models

Qwen3-8B-DSpine-b16: 4GB+ VRAM

Discover DSpine, a parallel draft model by Tencent for speculative decoding that enhances inference speed and accepta ...