$ ls ./menu

© 2025 ESSA MAMDANI

LIVE
AI Agent Stacks: Skills, Plugins, MCP, ACP, Memory and WorkflowsGrok 4.5: xAI's New Coding Model ExplainedGoogle Gemma 4 Vision Upgrade: 280 vs 1120 Soft Tokens for 2.51MP Sharp OCR — July 2026Kimi K3 Is Live: 2.8T Open Frontier IntelligenceJuly 2026 Frontier Model Comparison: 16 New Models from GPT-5.6 to Bonsai 27B — Complete Guide with Pricing & BenchmarksClaude Opus 4.8: 4x Safer Judgment, 88.6% SWE-Bench Flagship — May-June 2026 Deep DiveAI Agent Stacks: Skills, Plugins, MCP, ACP, Memory and WorkflowsGrok 4.5: xAI's New Coding Model ExplainedGoogle Gemma 4 Vision Upgrade: 280 vs 1120 Soft Tokens for 2.51MP Sharp OCR — July 2026Kimi K3 Is Live: 2.8T Open Frontier IntelligenceJuly 2026 Frontier Model Comparison: 16 New Models from GPT-5.6 to Bonsai 27B — Complete Guide with Pricing & BenchmarksClaude Opus 4.8: 4x Safer Judgment, 88.6% SWE-Bench Flagship — May-June 2026 Deep DiveAI Agent Stacks: Skills, Plugins, MCP, ACP, Memory and WorkflowsGrok 4.5: xAI's New Coding Model ExplainedGoogle Gemma 4 Vision Upgrade: 280 vs 1120 Soft Tokens for 2.51MP Sharp OCR — July 2026Kimi K3 Is Live: 2.8T Open Frontier IntelligenceJuly 2026 Frontier Model Comparison: 16 New Models from GPT-5.6 to Bonsai 27B — Complete Guide with Pricing & BenchmarksClaude Opus 4.8: 4x Safer Judgment, 88.6% SWE-Bench Flagship — May-June 2026 Deep DiveAI Agent Stacks: Skills, Plugins, MCP, ACP, Memory and WorkflowsGrok 4.5: xAI's New Coding Model ExplainedGoogle Gemma 4 Vision Upgrade: 280 vs 1120 Soft Tokens for 2.51MP Sharp OCR — July 2026Kimi K3 Is Live: 2.8T Open Frontier IntelligenceJuly 2026 Frontier Model Comparison: 16 New Models from GPT-5.6 to Bonsai 27B — Complete Guide with Pricing & BenchmarksClaude Opus 4.8: 4x Safer Judgment, 88.6% SWE-Bench Flagship — May-June 2026 Deep Dive
WebGPU • Live Inference • Zero Server Cost

Browser AI Playground
Run Bonsai 27B & Gemma 4 Vision in Your Browser

WebGPU is unlocking local inference at absurd scale. A 27B parameter model running directly in Chrome, on a 4GB Android phone — no server, no API, no cost. Just shaders, attention kernels, and the browser.

⚠️

Requires WebGPU-compatible browser. Chrome 113+, Edge 113+, or Chrome Canary. On some setups you may need to enable chrome://flags/#enable-unsafe-webgpu. Firefox support is experimental. Safari 18+ has partial WebGPU support. 4GB+ RAM recommended for 27B model (quantized to ~3-4 bits).

🧠 How does Bonsai 27B run in the browser?

WebML community compiles the model into WGSL compute shaders. Weights are quantized to 3-4 bits, KV-cache is tiled across GPU memory. The entire inference loop — tokenization, attention, FFN, sampling — happens on your GPU via WebGPU compute passes. Nothing leaves your device.

👁️ Gemma 4 Vision in-browser

Google's Gemma team ships a vision-language model that can caption images, answer visual questions, and reason over what it sees — all via WebGPU. Upload an image, ask a question, watch it think. No upload to a cloud.

Bonsai 27B — WebGPU Chat

27B param model running locally via WebGPU shaders. Try long-form reasoning, coding, creative writing.

Open in HF

Loading Bonsai 27B — WebGPU Chat...

WebGPU • HF Spaces • Zero Server

Gemma 4 Vision — Interactive (via HF Space)

Vision-language model from @googlegemma tweet. Upload images + Q&A. Interactive Space — open in HF for full demo.

Open in HF

Loading Gemma 4 Vision — Interactive (via HF Space)...

WebGPU • HF Spaces • Zero Server

Spaces hosted on HuggingFace. If an embed fails to load, use the "Open in HF" button. Some models may take 30–60s to initialize as weights download and shaders compile. First token is slowest; subsequent tokens stream fast. Built with WebGPU + WGSL.