Igor Lessio - Robots/acc - AIFlow Labs (@AIFlow_ML) header
Igor Lessio - Robots/acc - AIFlow Labs (@AIFlow_ML) profile picture

I run AIFLOW LABS. Daily Local AI brief: DGX Spark, open weights, desktop boxes. I also build robots. https://nitter.gq/t.co/bbTa7Fivjy

Phuket
Joined October 2023
Robot sim benchmarks have a physics problem. An audit of RoboDojo found loose joints and ignored material properties, and the maintainer agreed. If the sim physics is wrong, what did the leaderboard measure?
1
37
A 9B model at 59 tok/s on a 16 GB GPU. JJ Eaton @jayleaton ran SenseNova-Loop-9B on TensorFold: 59.1 tok/s on an RTX 5070 Ti, 59.5 on an M5 Ultra. Weak spot he flagged himself: tool calls, 58% on BFCL. Fine for chat on a cheap card. Not your agent brain yet.
1
5
127
WOT ??? Sense physical object in motion ? Best sensor ever !
🇨🇳 NEWS: China reports a 6G breakthrough as researchers trial technology able to sense physical objects in motion
54
FTX & EA founded with our money.
INTEL: FTX sold its Anthropic stake for $1.34 billion in 2024 and it is now worth about $39.6 billion
2
81
DeepSeek-V4.1-Flash at 59.5 tok/s on about 160 W. That's one M5 Ultra 512 GB, measured by Justin Kalland and shared by @OwnYourCompute. At home the power is the small part. The box is the real cost.
1
5
139
The new RTX Spark desktops use the same Grace CPU and Blackwell GPU class as DGX Spark, but ship 10GbE instead of ConnectX-7. No 200G link, so no two-box setups for the big MoEs. We run local inference on DGX Spark. If you might cluster later, buy the box with the 200G port.
3
2
141
Same RTX 5090, same small model, 4x the throughput. @flaviusburca tested 8 users at once: Surogate served 2,765 tok/s, llama.cpp 683. Single-user benchmarks hide this. Bench at the user count you really run.
2
1
117
Hy4 Flash read a 1M-token prompt in 44 min on a Mac Studio M3 Ultra and 81 min on a DGX Spark, per @Razumasu. Follow-ups on the cache took 2.8 s on the Mac, 3.4 on the Spark. Slow read once per doc. Which doc would you pre-read overnight?
1
99
Four DGX Sparks, one week of tuning, and code went from 26.85 to 56.71 tok/s. @arlogilbert also cut the slowest first token at 8 users from 64 s to about 1 s by raising the sequence cap. His biggest wins were a depth-3 drafter, FP8 attention (+12%) and a faster path for small all-reduces (+16%). Tune the four boxes you have before you buy a fifth.
1
93
Very good job Nvidia. Jail the board !
1
87
Nvidia bear market confirmed. Now we gonna see less loi.
1
2
144
OpenAI's coding agents now finish 46% of 2 to 4 hour research tasks with zero human help. In March it was 23%. By task, it's 79% on monitoring training runs and 25% on writing inference and serving code. Agents are good at watching. Still weak at building. Which job would you hand to an agent first?
2
82
Looking to buy one to use here in Thailand when shit will hit the fan big.
Plug straight into the sun and let the DJI Power Auro 2000 Elite fast-charge your entire ecosystem in the wild. Unfold the panels anywhere and turn sunlight into uninterrupted flight time. Pure off-grid power for endless creative sessions.
4
130
Wait till you will get to know that OpenClaw is just botnet to do data harvesting.
1
100
Monday is gonna be frisky frisky on the market !!
2
74
Monday im in Shenzhen. Let's rock !!
1
81