Deltafin

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

20:07

2026-09-08

github.com

large-language-models

Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs

Argonaut Labs AI's Deltafin fork runs the full, never-pruned 2.8-trillion-parameter Kimi K3 model on a MacBook Pro at 0.2901 tokens per second (3.447 seconds per token), streaming from four SSDs, achi…

21:35

2026-07-28

github.com

artificial-intelligence

Running Kimi K3 on a M1 Mac

Deltafin, a small research project, has successfully run the 2.8-trillion-parameter Kimi K3 Mixture-of-Experts model on a 64 GB M1 Max Mac at about 16 seconds per token, using a technique that streams…

// co-occurs with top 8 entities

Kimi K3 2 Moonshot AI 2 Apple M1 Max 1 OpenAI 1 Argonaut Labs AI 1 gavamedia/deltafin 1 ARGODRIVE 1 Apple Silicon 1

// topics top 5 topics

large language models 2 ai infrastructure 2 ai research 2 artificial intelligence 1 ai tools 1