FRAMEWIREIndonesiaUpdated Sep 8Live wire
0:00 / 0:00

DeepSeek V4 Flash Vision Abliterated vs GLM 5.3 Flash EXL3 running both on 2 sparks 👇

The question: What is the highest leverage thing humanity still doesn’t know that it could know in the next few decades? The question whose answer would most compress our ignorance about

Javier ⚛ priv/accSep 82
0:00 / 0:00

DeepSeek V4.1 Flash over the API is *really* fast!

🤯 Some details: • new architecture + native multimodality • 1M context window • same price as v4 Flash For me it seems to be (over)thinking a lot though.

Peter DedeneSep 81
0:00 / 0:00

The beta version of DeepSeek 4.1 Flash has recorded very fast performance in tests.

See the output speed test in this video: 👇

Legendary CoderSep 85
0:00 / 0:00

Deepseek-v4.1-flash I'm really curious to understand the architecture behind the scenes.

🤔 Model is really fast as you can see in the video! I've got an average decoding speed of around 350 t/s. BTW it is clearly experimental and: - currently, the model is under heavy load and

Ivan Fioravanti ᯅSep 837