Back to News
PrismMLJuly 14, 2026

Bonsai 27B

Open Source
LLM
On-device AI
Model Compression
Multimodal

Explore Bonsai 27B

Visit the official website to learn more and get started

### TL;DR

Bonsai 27B is a multimodal, 27-billion-parameter language model optimized for extreme on-device efficiency using 1-bit and ternary weight compression. It enables complex agentic workflows, multi-step reasoning, and tool use on consumer hardware like smartphones and laptops without requiring cloud connectivity.

Key Insights & Metrics

Pricing
Free
Cost structure
Version
N/A
Current release version
Hardware
High-end mobile devices (e.g., iPhone 17 Pro) for 1-bit variant; everyday laptops/GPUs for Ternary variant
Compute requirements
Category
Open Source
Licensing model
Region
United States
Primary region

Key Features

  • 1-bit and Ternary weight compression achieving a 3.9GB-5.9GB footprint
  • Multimodal capabilities supporting vision tasks like screenshots, documents, and camera input
  • Full 262K-token context window
  • Optimized for on-device agentic loops and autonomous tool-calling
  • Supports speculative-decoding for accelerated token generation
  • End-to-end local execution via Apple MLX and NVIDIA CUDA

Discussion

0
Upvotes
0
Downvotes
0 reviews

Sign in to leave a review

Reviews

No reviews yet. Be the first to review!

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode