skills.rest
ricable
ricableCOMMUNITY
Explore all skills by this author →
GitHub

ruvector-ruvllm-wasm

Run WebAssembly LLM inference in browsers with WebGPU acceleration.

1|Updated Feb 8, 2026
Search Tags:#embeddings#llm#wasm#webgpu#text generation#edge ai#browser inference
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-ruvllm-wasm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ruvector-ruvllm-wasm
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/ruvector-ruvllm-wasm
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-ruvllm-wasm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables running powerful Large Language Models (LLMs) directly within a web browser, even on edge devices, without needing a server.

Core Features & Use Cases

  • Client-Side LLM Inference: Perform text generation, embedding, and streaming completions directly in the browser.
  • WebGPU Acceleration: Leverages WebGPU for fast, hardware-accelerated inference.
  • Quantized Models: Supports loading smaller, quantized models for efficient use of memory and bandwidth.
  • Use Case: Build offline-capable AI chat applications, add text generation features to web apps, or deploy language models to resource-constrained edge devices.

Quick Start

Use the ruvector-ruvllm-wasm skill to generate text using the 'tinyllama-1.1b-q4' model in the browser.

Frequently Asked Questions about ruvector-ruvllm-wasm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run LLM inference in the browser without a backend server?▼

Browser LLM inference uses WebAssembly bindings and WebGPU acceleration to execute quantized language models directly on the client side, enabling offline-capable text generation without server dependencies.

What is WebGPU acceleration for client-side text generation?▼

WebGPU acceleration provides hardware-accelerated processing for client-side text generation, allowing WebAssembly-compiled language models to execute efficiently within the browser environment using local GPU resources.

Can I use quantized models for edge AI deployment in web applications?▼

Quantized models are supported for edge AI deployment, allowing web applications to load smaller model formats that optimize memory and bandwidth usage while performing browser-based inference on resource-constrained devices.

Does WebAssembly support streaming text generation and embeddings in web apps?▼

WebAssembly supports streaming text generation and embeddings in web apps by binding LLM inference capabilities directly to the browser, facilitating real-time completions and vector generation without external network calls.

What is the best way to build an offline AI chat application for edge devices?▼

Building an offline AI chat application for edge devices requires WebAssembly and WebGPU to load quantized LLMs locally, ensuring text generation and streaming completions operate independently of network connectivity.

Are there limitations when using quantized models for browser inference?▼

Quantized models for browser inference reduce memory and bandwidth but may trade generation fidelity for size, requiring WebGPU support and WebAssembly compatibility to execute efficiently on constrained edge devices.

Related Skills

Explore More Software Engineering Skills→
pmcdowallpmcdowall

gguf-quantization

Convert Hugging Face models into GGUF format with 2-8 bit quantization.

Community
Advanced
J4JoshuaJ4Joshua

ollama

Serve local language and embedding models offline on Apple Silicon.

Community
Advanced
datamonsterrdatamonsterr

qdrant

Integrate Qdrant vector database with Java Spring Boot and LangChain4j.

Community
Advanced
artmsilvaartmsilva
2

check-rsc-compat

Audit Stitches RSC components for React Server Components compatibility issues.

Community
Intermediate