For dual DGX spark users; GLM 5.3 flash got a 50%+ performance boost

For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parallel, totalling around 200 tps cumulative decode. Because of this, I did not feel like switching to GL

中文全文翻译正在补齐，可先查看下方英文原文。

For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parallel, totalling around 200 tps cumulative decode. Because of this, I did not feel like switching to GL