Gallery
About
We took a recently released Bonsai 1.7B ternary model from PrismML (https://github.com/PrismML-Eng/Bonsai-demo) and ran our agentic evolution search on it for 6 hours to optimize the Metal kernels. The search was fully autonomous.Measured against unmodified upstream llama.cpp at the same Bonsai/Q2_0 commit, same M4 Max:- tg128: 309.82 → 442.42 t/s (+42.0%)- pp512: 4250.32 → 4622.63 t/s (+8.8%)
Comments (0)
No comments yet. Be the first to comment!
Related Products
Parse LLM Markdown streams incrementally on the server or client
Find the best local LLM for your hardware, ranked by benchmarks
Watch a neural net learn to play Snake
JDS – a Copilot skill suite for structuring AI coding behavior
Find the best local LLM for your hardware, ranked by benchmarks
Containarium – self-hosted sandbox for AI agents, MCP-native