Sebastian Christiansen
@CerebralCoding_
Senior software engineer
Automation + applied AI (pharma)
Contributor: MLX-Serve, TensorFold, ds4
Local inference · Real hardware · Builders
514 Following 2.3K Followers
Drafter speedups are not a 256 token demo trick.
M5 Max, TensorFold, Qwen3.8 27B: 129 tok/s across 162K tokens of long output, against 24 tok/s with drafting off. 30 runs, 2.7K to 8.2K tokens each, three sampling settings.
5x holds when the answers get long.
Show more
@aijoey @ashxhart @ViC305 @mr_r0b0t @0xBakeer @mmastrac @ToNYD2WiLD @u1tra_instinct @Blackwellboy @SpaceTimeViking @coldniko @ddalcu - MLX-Serve
@Beamsters1 - Sushi
@TheDavidTai - EigenLabs, Yukon, MLX-Stream
@CerebralCoding_ for various work on both MLX-Serve and TensorFold 😬
Show more
Most AI Twitter ships demos. I ship stuff that runs on a Mac with the lid closed.
MLX-Serve. TensorFold. Local agents that don't phone home.
Sitting at 197 followers and hunting 250 by tonight. If you're building local Apple Silicon AI, say hi. #connect#
Show more
