Bonsai — A drop-in optimized inference build of Bonsai 1.7B for Apple Silicon · dotstore

Description

A drop-in optimized inference build of Bonsai 1.7B for Apple Silicon. ~42% faster decode (tg128) and ~9% faster prefill (pp512) on M-series GPUs. All Metal kernels written and tuned by ata, our autonomous engineering agent.…

Ratings & Reviews

No ratings yet

Be the first to rate Bonsai.

People also visit

E

Embedding.io

Turn websites into knowledge bases

AI

R

RLAMA

Complete AI Platform: RAG Systems & Intelligent Agents for Local AI

AI

T

TypingMind

Alternative web UI

AI

I

Inspector

Testing and evaluation platform to chat, inspect, and debug MCP servers

AI

C

Conductor

Run a team of coding agents in the cloud

AI

M

Moltis

A secure persistent personal agent server in Rust

AI

See all Bonsai alternatives

Bonsai FAQ

What is Bonsai?

A drop-in optimized inference build of Bonsai 1.7B for Apple Silicon. ~42% faster decode (tg128) and ~9% faster prefill (pp512) on M-series GPUs. All Metal kernels written and tuned by ata, our autonomous engineering agent.

Do I need to download Bonsai?

No. Bonsai runs in your browser at agents2agents.ai, so there's nothing to install.

What are the best Bonsai alternatives?

Popular alternatives to Bonsai include Embedding.io, RLAMA and TypingMind. See all Bonsai alternatives

Developer Stuff

Badges