Tencent just released WeDLM 8B, it's a diffusion language model that runs 3-6× faster than vLLM-optimized Qwen3-8B on math reasoning tasks.
Tencent just released WeDLM 8B, it's a diffusion language model that runs 3-6× faster than vLLM-optimized Qwen3-8B on math reasoning tasks.
huggingface.co
tencent/WeDLM-8B-Base · Hugging Face
instruct model https://huggingface.co/tencent/WeDLM-8B-Instruct