GLM 5.3 Flash Q4 @ 60tps / 550tps on M3 Ultra

I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it. In the screenshot you can see the outcome of using the model with a claude code harness at ~200k depth, with many tool calls and averaging over 38tps output. Yes

中文全文翻译正在补齐，可先查看下方英文原文。

I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it. In the screenshot you can see the outcome of using the model with a claude code harness at ~200k depth, with many tool calls and averaging over 38tps output. Yes