FRAMEWIREIndonesiaUpdated Sep 5Live wire
0:00 / 0:00

On the flight I tried MTPLX and ds4 with Qwen 3.8 Flash Next on M5 Max in Low Power.

Not bad! In ds4 I've not cooked support for MTP in ds4 chat. - MTPLX 25 t/s - DS4 18 t/s

Ivan Fioravanti ᯅSep 547
0:00 / 0:00

Qwen 3.8: 27b on fire 🔥 someone is burning 1500tok/sec.

Hermes Agent Super-IntelSep 59
0:00 / 0:00

What are people getting w/ Qwen-3.8-27B on M5 Pro with 24gb?

I think we might be close to 2x'ing (this: with the iPhone handling spec decode and mac handling verification. probably some room to improve here. Just glad that my 24gb machine might not be

Rohan AroraSep 56
0:00 / 0:00

GLM-5.3 Flash and Qwen 3.8 Flash same instructions in Topview Canvas.

1 same image. Same Seedance 2.5. The only difference is the LLM that wrote the prompt. ・The only thing I asked LLM to write was "one prompt." The generation conditions are fixed here and the same conditions ・480p / 16:9 / 15 seconds / One shot / No retry

右よし左よし秋よし@AIエンタメSep 52