PrismML-Eng/Bonsai-demo
Bonsai Demo
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 57 contributors on GitHub.
Peaked at #98 in the weekly ranking the week of Jul 19, its best in the past year.
Use Cases & Benefits
- Runs Bonsai and Ternary-Bonsai language models locally with support for vision, chat, and tool calling across multiple platforms and hardware backends.
- Offers ultra-efficient 1-bit and 2-bit quantized models enabling large-scale vision-language and reasoning tasks on consumer devices with minimal memory footprint.
- Use for deploying large context (up to 262k tokens) vision-language chatbots on local machines without cloud dependency.
- Use for experimenting with agentic tool calling and native OpenAI-style tool integration in custom AI workflows.
- Use for benchmarking and developing on diverse hardware including Mac (Metal), Linux/Windows (CUDA, Vulkan, ROCm), and CPU-only environments.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Using this demo repository you can run Bonsai (1-bit) and Ternary-Bonsai language models locally on Mac (Metal), Linux/Windows (CUDA, Vulkan, ROCm), or CPU.
The family's newest and largest generation, and its first vision-language models (Bonsai 27B collection):
Quick Start below gets you there in two commands:
./setup.shdownloads Ternary-Bonsai-27B by default, then./scripts/start_llama_server.shgives you chat, vision, and tools at http://localhost:8080.Setting things up with an AI coding agent? Point it at AGENTS.md, a guide written for agents (hardware-specific knobs, defaults, and what to ask the user).
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+1,303 stars over 85 days across 8 snapshot days; best day +13 on Aug 14.
Forks
395+175
Open issues
22+6
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| NVIDIA/auto-ontology | 7.5K | +5.6K | 37 | — |
| HKUDS/DeepTutor | 55.5K | +5.5K | 65 | 5 days ago |
| affaan-m/ECC | 297.9K | +5.2K | 63 | 35 days ago |
| DietrichGebert/ponytail | 185.3K | +5.1K | 60 | 7 days ago |
| PrismML-Eng/Bonsai-demo | 3.5K | — | 35 | — |
| Category median | 113.6K | +5.5K | 60 | — |
Discover Repositories
Search across tracked repositories by name or description