Ternary Bonsai WebGPU
Chat with 1.58-bit Bonsai language models running locally in your browser on WebGPU.
Artifact by webml-community
Use it
Opens huggingface.co in a new tab. Nothing to install.
- You provide
- a chat message
- You get
- a text reply
- Account
- Not stated
- AI
- No AI: a plain tool
- Your input
- Not stated: check the tool's privacy notes before using private data
- Price
- Free to use
- Made with
- Hugging Face Space (static)
- Source
- Open source
- Link check
- Answered on Oct 31, 2026
About
Category: AI assistants
Reviews
Write a reviewNo reviews yet. Used it? Sign in with an established GitHub account to rate it. How reviews work
More ai assistants tools
- 0.867score
Chatbox Web
Chatbox
Web version of the Chatbox client for chatting with models from several providers using your own keys.
ArtifactAINo sign-up★ 42.2Kai assistants - 0.827score
Better ChatGPT
ztjhz
Browser chat interface for the OpenAI API with prompt library, folders and local history; bring your own key.
ArtifactAINo sign-up★ 8.4Kai assistants - 0.791score
Anse
anse-app
Open-source web chat front end that works with several AI providers using keys you supply.
ArtifactAINo sign-up★ 2Kai assistants - 0.784score
wllama Demo
ngxson
Loads a GGUF model with a WebAssembly llama.cpp build and generates text in the browser.
ArtifactAINo sign-upIn-browser★ 1.4Kai assistants - 0.779score
WebLLM Chat
MLC AI
Chat with open language models that download into your browser and run on WebGPU without a server.
ArtifactAINo sign-upIn-browser★ 1.1Kai assistants - 0.778score
Hollama
fmaclen
Minimal web interface for chatting with models served by Ollama or OpenAI-compatible servers.
ArtifactAINo sign-up★ 1.2Kai assistants
Signals
- Hugging Face likes
- 165
- Last commit
- Apr 16, 2026 (6 months ago)
From Hugging Face.
Details
- License
- Open source
- First seen
- Oct 31, 2026
- Last checked
- Oct 31, 2026
- Source
- Hugging Face
More from webml-community
- 0.627score
Gemma 4 WebGPU Kernels
webml-community
Runs a Gemma 4 model in the browser with custom WebGPU kernels, so chat needs no server.
ArtifactAINo sign-upIn-browser★ 332ai assistants - 0.611score
SmolVLM Realtime Camera
webml-community
Points your webcam at a scene and has a small vision-language model describe it continuously, locally on WebGPU.
ArtifactAINo sign-upIn-browser★ 160ai assistants - 0.595score
Qwen 3.5 In-Browser Vision Chat
webml-community
Multimodal chat with Qwen 3.5 vision models running locally via Transformers.js and WebGPU.
ArtifactAINo sign-upIn-browser★ 98ai assistants - 0.592score
Nemotron 3 Nano WebGPU
webml-community
A compact reasoning-capable Nemotron model that runs in the browser on WebGPU.
ArtifactAINo sign-upIn-browser★ 86ai assistants - 0.589score
GPT-OSS 20B WebGPU
webml-community
Loads the open-weight GPT-OSS 20B model into WebGPU memory so you can chat without a server.
ArtifactAINo sign-upIn-browser★ 76ai assistants - 0.589score
LFM2.5 230M WebGPU
webml-community
Runs the very small LFM2.5 230M language model with custom WebGPU kernels in the tab.
ArtifactAINo sign-upIn-browser★ 75ai assistants
Cite this page
Ternary Bonsai WebGPU: free online tool. Agent Mart. https://agentmart.dev/artifacts/ternary-bonsai-webgpu (last updated 2026-10-31)