← Back to Compatibility

Chrome Desktop

Full LocalMode support on Chrome Desktop - WebGPU, WASM, IndexedDB, Web Workers, and all 136 curated models.

Chrome Desktop

Full LocalMode support on Chrome Desktop - WebGPU, WASM, IndexedDB, Web Workers, and all 136 curated models.

Category: Browser Compatibility

Feature Support Matrix

The following table summarizes which web platform features are available on Chrome Desktop and how they affect LocalMode's capabilities. Features marked as supported enable full functionality; partial or unsupported features trigger automatic fallbacks.

FeatureSupportedNotes
WebGPUYes (Chrome 113+)Full WebGPU support. Required for WebLLM. Enables fastest LLM inference (30-90 tok/s).
WebAssemblyYes (Chrome 57+)Full WASM + SIMD support. Required for wllama and Transformers.js.
IndexedDBYesFull support. Used for VectorDB persistence and model caching. Quota: up to 60% of total disk size per origin (Chrome).
Web WorkersYesFull support including module workers. Enables background model loading and inference.
SharedArrayBufferYes (with COOP/COEP headers)Requires Cross-Origin-Opener-Policy and Cross-Origin-Embedder-Policy headers.
Web LocksYes (Chrome 69+)Full support. Used for cross-tab model loading coordination.
BroadcastChannelYes (Chrome 54+)Full support. Used for cross-tab VectorDB sync.
Chrome Built-in AIChrome 138+ (Summarizer/Translator stable, Prompt API origin trial)@localmode/chrome-ai for zero-download summarization and translation via Gemini Nano.

Understanding the Impact

Each feature in the matrix above maps to specific LocalMode capabilities:

  • WebGPU - Required for @localmode/webllm (GPU-accelerated LLM inference at 30-90 tokens/second). When unavailable, use @localmode/wllama (WASM, 5-20 tokens/second) as a fallback. Non-LLM tasks (embeddings, classification, vision, audio) do not require WebGPU.
  • WebAssembly - The universal inference backend. Required for @localmode/transformers and @localmode/wllama. WASM is supported in 97%+ of web traffic. SIMD support (for optimized vector operations) requires newer browser versions.
  • IndexedDB - Used for persistent vector storage (VectorDB) and model caching (createModelLoader). When blocked (Safari Private Browsing), LocalMode falls back to MemoryStorage (data lost on tab close).
  • Web Workers - Enable background model loading and inference without blocking the main UI thread. Module workers (for ES module imports in workers) require newer browser versions.
  • SharedArrayBuffer - Enables multi-threaded WASM inference for improved performance. Requires Cross-Origin Isolation headers (COOP/COEP). Not required for basic functionality.
  • Web Locks - Used for cross-tab model loading coordination (prevents multiple tabs from downloading the same model simultaneously). Falls back to InMemoryLockManager when unavailable.
  • BroadcastChannel - Used for cross-tab VectorDB synchronization. Falls back to LocalStorageBroadcaster when unavailable.

Fallback Strategies

Chrome Desktop supports all LocalMode features. No fallbacks needed. This is the recommended development target - if your app works in Chrome Desktop, you've covered the majority of your user base. The main consideration is WebGPU availability: Chrome 113+ has full support, but users on Chrome 80-112 will fall back to WASM-based inference (wllama, Transformers.js).

LocalMode is designed with progressive enhancement in mind. The core principle: detect capabilities at runtime and use the best available path. The @localmode/core package exports detection utilities for this purpose:

import {
  isWebGPUSupported,
  isIndexedDBSupported,
  isCrossOriginIsolated,
  detectCapabilities,
  recommendModels,
} from '@localmode/core';

async function detectAndConfigure() {
  const caps = await detectCapabilities();
  console.log(caps);
  // caps.features.webgpu, caps.hardware.memory (GB), caps.storage.availableBytes

  // isWebGPUSupported() is async - it must be awaited
  if (await isWebGPUSupported()) {
    // Use @localmode/webllm for GPU-accelerated inference
  }

  // recommendModels() is synchronous: capabilities first, options second
  const recommendations = recommendModels(caps, {
    task: 'generation',
    maxSizeMB: 1500,
  });
}

For Chrome Desktop, the recommended LocalMode providers are:

  • WebLLM (WebGPU) - Use when WebGPU is confirmed available. Provides the fastest LLM inference.
  • wllama (WASM) - Universal LLM inference via WASM. Works without WebGPU. The safe choice for broad compatibility.
  • Transformers.js - Broadest model catalog for non-LLM tasks (embeddings, classification, vision, audio). WASM-based, works everywhere.
  • Chrome Built-in AI - Zero model download. Requires Chrome 138+ with flag. Provides summarization, translation, and writing assistance via Gemini Nano.

The following models are tested and recommended for Chrome Desktop:

ModelProvider
Qwen3-4B-q4f16_1-MLCWebLLM (WebGPU)
Xenova/bge-small-en-v1.5Transformers.js
onnx-community/moonshine-base-ONNXTransformers.js

These models are chosen for their compatibility with Chrome Desktop's capabilities and constraints. They represent the best balance of quality, size, and performance for this platform.

Known Issues

Memory pressure: Chrome may evict IndexedDB data under storage pressure. Use navigator.storage.persist() to request persistent storage. GPU memory: Large WebLLM models (4GB+) may compete with browser rendering for GPU VRAM - monitor for visual glitches on integrated graphics.

Mitigation Strategies

When building applications that target Chrome Desktop, follow these practices:

  1. Always detect before loading - Use await isWebGPUSupported(), isIndexedDBSupported(), and await detectCapabilities() before attempting to load models or create storage. Never assume a feature is available.
  2. Wrap model loading in try/catch - Even when detection succeeds, model loading can fail due to memory pressure, network issues, or browser bugs. Always have a fallback path that attempts a smaller model.
  3. Pick models with recommendModels() - Pass the detected capabilities to recommendModels(caps, { task }) to select a model appropriate for the current device. It is the recommended pattern for production deployments.
  4. Test on real hardware - Browser DevTools device emulation does not accurately simulate memory limits, GPU capabilities, or storage quotas. Test on actual target hardware.
  5. Monitor storage quota - Use getStorageQuota() to check available space before downloading large models. Inform users if storage is insufficient rather than failing silently.

Web Standards References

Methodology

Browser feature support data on this page is sourced from caniuse.com support tables and MDN Web Docs compatibility tables, cross-referenced with LocalMode's runtime feature detection (packages/core/src/capabilities/features.ts). Version numbers reflect the Chrome stable release in which each feature shipped enabled by default: WebGPU (Chrome 113, confirmed via caniuse.com and the official Chrome launch post), WebAssembly (Chrome 57), Web Locks (Chrome 69), BroadcastChannel (Chrome 54). The IndexedDB storage quota (up to 60% of total disk size per origin) is sourced from the MDN Storage quotas and eviction criteria article. Chrome Built-in AI API stable availability is sourced from the Chrome for Developers I/O 2025 announcement. Browser support evolves - verify current support with the linked Sources before making production decisions.

Sources