Bonsai 2 9B: 4–6x faster decoding on Mac and DGX Spark
A one-week open challenge pushed Bonsai 2 9B decode speed to 959 tok/s on Apple Silicon and 576 tok/s on DGX Spark, with leaderboard records set by humans and agents including Gemini 4 Argon.
🏁 FINAL RESULTS: Bonsai 2 9B now runs 471% faster on Macs and 421.5% faster on NVIDIA DGX Spark. Open frontier research and open-weight models win again. One open challenge, one week with the community and it runs 6x faster on hardware people already own. It is crazy to see that the decode speed went from 144.8 to 959.6 tokens/sec on Apple Silicon and from 85.9 to 576.7 on DGX Spark. This model can also run on an iPhone. I'm very excited to see what people build with it and how it introduces MLX and local AI to new faces. Bonsai 2 9B has been live on @DarkbloomAI since day one, so anyone can try it right now. 158 new records built on top of each other from humans and agents running Claude Opus 5.5, GPT-6.1 Sol, GPT-6 Astra, Gemini 4 Argon, DeepSeek-V4 and Qwen3.8-Flash-Next. Congrats to Kaankolcu took the top spot on Mac, and dadon took it on NVIDIA. Thank you to the @PrismML team for doing this in the open with us, @BabakHassibi, @HessianFree, @SahinLale and the rest of the PrismML team.