Skip to main content

AI & Machine Learning Tools

Train neural networks in your browser, count LLM tokens, calculate VRAM requirements, and estimate AI infrastructure costs

11 tools available
🧠

Neural Network Playground

Train a real neural network in your browser — no code, no installs. Pick a sample dataset (Titanic survival, vehicle classifier, handwritten digits) or upload your own CSV, watch the network learn with live visuals, then ask it questions and export the model as Python/Keras code.

Try it now
🔢

LLM Token Counter

Count tokens in text for GPT, Claude, Gemini, and open models like Llama, Gemma, and Qwen — or search any model on Hugging Face. Estimate API costs, check context window fit, and optimize prompts

Try it now
🤖

AWS Bedrock Pricing Calculator

Calculate AWS Bedrock costs for Claude, Llama, Titan, and other AI models. Estimate input/output token costs for your workload

Try it now
🧠

LLM VRAM Calculator

Calculate how much VRAM any LLM needs to run locally — pick a model (Llama, Gemma, Qwen, DeepSeek, or search Hugging Face), choose a quantization and context size, and see which GPUs it fits on, including multi-GPU setups.

Try it now
⚡

LLM Inference Speed Calculator

Estimate LLM tokens per second from memory bandwidth, model size, quantization, and context window. Compare generation speed across GPUs (RTX 4090, 5090, A100, H100, Apple Silicon) and understand the memory-bandwidth bottleneck.

Try it now
🎯

What LLM Can I Run?

Detect your GPU with one click and see which LLMs your computer can actually run — Llama, Gemma, Qwen, DeepSeek and 50+ more, ranked by whether they fit in your VRAM, need CPU offloading, or won't run at all.

Try it now
🎛️

Fine-Tuning VRAM Calculator

Calculate VRAM requirements for fine-tuning LLMs with full fine-tuning, LoRA, or QLoRA. Accounts for gradients, optimizer states, activations, batch size, and gradient checkpointing — see which GPUs can train each model.

Try it now
🦙

Ollama Command Builder

Build Ollama commands without memorizing syntax: run, pull, and create commands for any model, complete Modelfiles with parameters and system prompts, and server environment configuration — with built-in VRAM checks.

Try it now
💰

Self-Hosted LLM Cost Calculator

Is it cheaper to self-host an LLM or use an API? Compare GPT, Claude, and Gemini API costs against running open models on your own hardware or cloud GPUs — with break-even timelines and capacity checks.

Try it now
🏁

LLM GPU Benchmark

Speed test your GPU for AI — measure real memory bandwidth and compute with WebGPU, run an actual LLM in your browser to measure true tokens/sec, and see predicted speeds for every popular model on your hardware.

Try it now
🤖

AI Gateway Selector

Find your AI gateway across Cloudflare AI Gateway, Portkey, LiteLLM, Helicone, Langfuse, LangSmith, Bedrock Guardrails, and OpenRouter. Filter by self-hosted, caching, rate limiting, and guardrails.

Try it now

Hands-on tools for working with AI and machine learning — from learning how neural networks actually work to planning LLM deployments. Train a real neural network in your browser and watch backpropagation happen live, count tokens to estimate API costs, calculate how much VRAM a model needs to run locally, and compare inference speed across GPUs.

Everything runs client-side in your browser: no accounts, no API keys, and your data never leaves your device. Whether you're a student learning the fundamentals, a developer planning a local LLM setup, or an engineer estimating cloud AI costs, these tools give you concrete answers fast.

Who Uses These Tools

Students and developers learning how neural networks, backpropagation, and gradient descent actually work

Engineers sizing GPU hardware for local LLM deployments (VRAM and tokens-per-second estimates)

Teams estimating OpenAI, Anthropic, and AWS Bedrock API costs from token counts

Architects choosing AI gateways and routing infrastructure for production LLM applications

Explore Other Categories

Planning

23 tools

Security

92 tools

Network

14 tools

Developer

90 tools

Media

5 tools

Compliance

15 tools

Assessment

7 tools

Vendor Comparison

18 tools

Need Expert Help?

Our tools can help you assess your needs, but sometimes you need expert guidance. Let's talk about your cybersecurity challenges.

Schedule a ConsultationView Our Services

Frequently Asked Questions

Do these tools send my data to AI providers?

No. All AI & ML tools run entirely in your browser. The Neural Network Playground trains models on your device, the token counter processes text locally, and the calculators work from published model specifications. Nothing is sent to OpenAI, Anthropic, or any other provider.

Can I really train a neural network without code or a GPU?

Yes. The Neural Network Playground implements the full training pipeline (forward pass, backpropagation, gradient descent) in JavaScript and runs it in a background thread on your CPU. Sample datasets train in under a minute. It is the same math used by TensorFlow and PyTorch, at a smaller scale.

How accurate are the VRAM and inference speed estimates?

The calculators use published model architectures and standard formulas (parameter count × bytes per parameter + KV cache + overhead). Real-world numbers vary with your inference framework and settings, but the estimates are typically within 10-15% — accurate enough for hardware planning decisions.

Which LLMs do the token and cost tools support?

The token counter supports GPT-4/GPT-3.5 (tiktoken), Claude, and Llama-family tokenizers. The AWS Bedrock calculator covers Claude, Llama, Titan, and other Bedrock models. The VRAM calculator works with any model on Hugging Face plus popular open models like Llama, Gemma, Qwen, and DeepSeek.