2 36 232

CHONG YOE YAT

CHONGYOEYAT

http://www.fmcv.my

cyysky

AI & ML interests

LLM,CNN

Recent Activity

liked a model about 6 hours ago

AIDC-AI/Marco-MT-Algharb

liked a model about 6 hours ago

inclusionAI/Ming-UniAudio-16B-A3B

reacted to mitkox's post with 🚀 about 6 hours ago

I run 20 AI coding agents locally on my desktop workstation at 400+ tokens/sec with MiniMax-M2. It’s a Sonnet drop-in replacement in my Cursor, Claude Code, Droid, Kilo and Cline peak at 11k tok/sec input and 433 tok/s output, can generate 1B+ tok/m.All with 196k context window. I'm running it for 6 days now with this config. Today max performance was stable at 490.2 tokens/sec across 48 concurrent clients and MiniMax M2. Z8 Fury G5, Xeon 3455, 4xA6K. Aibrix 0.5.0, vLLM 0.11.2,

View all activity

Organizations

liked 2 models about 6 hours ago

AIDC-AI/Marco-MT-Algharb

Translation • 15B • Updated Oct 23 • 613 • 23

inclusionAI/Ming-UniAudio-16B-A3B

Any-to-Any • 18B • Updated about 16 hours ago • 661 • 71

reacted to mitkox's post with 🚀 about 6 hours ago

Post

1681

I run 20 AI coding agents locally on my desktop workstation at 400+ tokens/sec with MiniMax-M2. It’s a Sonnet drop-in replacement in my Cursor, Claude Code, Droid, Kilo and Cline peak at 11k tok/sec input and 433 tok/s output, can generate 1B+ tok/m.All with 196k context window. I'm running it for 6 days now with this config.

Today max performance was stable at 490.2 tokens/sec across 48 concurrent clients and MiniMax M2.

Z8 Fury G5, Xeon 3455, 4xA6K. Aibrix 0.5.0, vLLM 0.11.2,