llamaperf

GLM-5.3 320B (18B active) Flash

on M3 Ultra 256GB · 300,000 ctx

Tone: positiveApple hardware
Sep 9, 2026
Throughput
37.4 t/s gen · 550.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q4
System RAM
256 GB

Use cases

agenticcodingtool-use

Summary

User reports GLM-5.3-Flash Q4 at 37.4 t/s end to end at 300k context on an M3 Ultra, against 21.6 t/s for stock ds4. Setup is a ds4 branch tuned for the M3 Ultra, decoding serially in a single stream without the dflash drafter, with prefill at 550 t/s at 62k. Serial decode rises from 29 to 40 t/s at short context and from 24 to 38 at 62k. In a claude code harness at ~200k depth it averages over 38 t/s output and reaches 60 t/s writing SQL, where the optional dflash drafter adds +20 to +50 percent.