RustyTorch++ WASM Inference Benchmark
Comparing RustyTorch WASM vs ONNX.js vs TensorFlow.js
System Information
Browser
Detecting...
Platform
Detecting...
WebAssembly
Checking...
SIMD
Checking...
Threads
Checking...
Memory
Checking...
Benchmark Configuration
Model Size
Tiny (~10M params)
Small (~50M params)
Medium (~100M params)
Sequence Length
32 tokens
64 tokens
128 tokens
256 tokens
Iterations
Warmup
Run Benchmarks
Click "Run Benchmarks" to start
Inference Latency (lower is better)
Throughput (higher is better)
Memory Usage (lower is better)
Model Load Time (lower is better)
Detailed Results
Framework
Avg Latency (ms)
P50 (ms)
P99 (ms)
Throughput (tok/s)
Memory (MB)
Load Time (ms)
vs RustyTorch
No benchmark results yet. Click "Run Benchmarks" to start.
Export Results
Download JSON
Download CSV