FRAMEWIREIndonesiaUpdated Sep 29Live wire
0:00 / 0:00

DeepSeek V4.1 Flash (2-bit MoE, experts streamed from SSD) on M5 Max

Decode 12.7 -> 24.1 tok/s averaged over 2048 tokens (~1.9x), output bit-identical to upstream main. Video: a 256-token run. ~18 tok/s while the expert cache warms up, then 24-26 tok/s. What this branch changed:

NOGUCHI, ShojiSep 29
0:00 / 0:00

Want to try an AI model for a coding task without creating an account?

Antseed says DeepSeek V4.1 Flash is currently free to use. Start at then use its desktop app or CLI (a text-based way to run tools) to try the model. The source also says it works

Tung AirSep 291
0:00 / 0:00

Long live Sardar Bhagat Singh!

Sikh Student Federation Zindabad

DeepSeekSep 2913
0:00 / 0:00

DeepSeek Harness is now on desktop—and OpenDesign Go works with it via API keys.

$8 first month. Up to 300K requests/mo. 10 benchmark-curated models for design, including GPT-6 Luna and DeepSeek V4.1 Flash.

OpenDesignSep 2923