wizenheimer/tinylm
Browser based ML Inference | OpenAI compliant | Run models like DeepSeek, Llama 3.2, NomicEmbed, KokoroTTS, and more
This helps web developers integrate advanced AI capabilities directly into web browsers and Node.js applications. It allows them to take user input text and generate responses, create text embeddings for search or analysis, and even produce spoken audio, all running on the client-side. The target users are web and JavaScript developers building interactive applications that leverage AI without needing a backend server.
No commits in the last 6 months.
Use this if you are a web developer looking to embed AI features like text generation, semantic search, or text-to-speech directly into your client-side applications for real-time, cost-effective inference.
Not ideal if you need to train large AI models or require server-side processing for complex, high-throughput AI workloads.
Stars
52
Forks
8
Language
TypeScript
License
—
Category
Last pushed
Mar 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/wizenheimer/tinylm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lfnovo/esperanto
A unified interface for various AI model providers
apocas/restai
RESTai is an AIaaS (AI as a Service) open-source platform. Built on top of LlamaIndex &...
baidubce/bce-qianfan-sdk
Provide best practices for LMOps, as well as elegant and convenient access to the features of...
sbhjt-gr/InferrLM
On-device AI for iOS & Android
ProviderProtocol/ai
0-DEP AI DX SDK