WebInfer
Configure Transformers.js
Enable Transformers.js in Settings
About Transformers.js
Run Hugging Face Transformers models directly in the browser or server-side using WebGPU/WebAssembly. No API keys required, fully local inference with support for chat, vision, embeddings, and transcription.
Key Features
- Runs fully in browser or Node.js
- WebGPU acceleration for fast inference
- Support for chat, vision, embeddings, transcription
- Model download progress tracking
- Web Worker support for off-main-thread execution
- No API keys or cloud dependency
Capabilities
chat
vision
embeddings
transcription
local
browser
webgpu
Configuration Schema
Required and optional fields for configuring this provider
| Field | Type | Required |
|---|---|---|
| modelId | text | Required |
| device | text | Optional |
| dtype | text | Optional |
CLI Usage
For users running the daemon server locally or a self-hosted gateway
Add provider:
npx webinfer provider add transformersjsTest connection:
npx webinfer provider test transformersjsProgrammatic Usage
Use Transformers.js in your code with WebInfer
Basic usage:
import { generateText } from "webinfer"
// WebInfer automatically routes to the best available provider
const result = await generateText({
prompt: "Write a haiku about programming"
})
console.log(result.text)Specify Transformers.js explicitly:
import { generateText } from "webinfer"
const result = await generateText({
prompt: "Write a haiku about programming",
provider: "transformersjs",
model: "HuggingFaceTB/SmolLM2-360M-Instruct"
})
console.log(result.text)
console.log("Provider:", result.provider)
console.log("Model:", result.model)Streaming:
import { streamText } from "webinfer"
const { textStream } = await streamText({
prompt: "Write a story about AI",
provider: "transformersjs"
})
for await (const chunk of textStream) {
process.stdout.write(chunk)
}Pricing
Free
Completely free. All computation happens locally on your device.