diff --git a/wasm/index.html b/wasm/index.html new file mode 100644 index 00000000..5e2e63c7 --- /dev/null +++ b/wasm/index.html @@ -0,0 +1,144 @@ + + + + +TurboQuant WASM Inference + + + +

TurboQuant WASM Inference

+

Run quantized models directly in the browser via WebAssembly. No server. No data leaves your machine.

+ +
+

1. Initialize

+ +not started +
+ +
+

2. Load Model

+ + +waiting +
+ +
+

3. Inference

+ +
+ + + + +
+
+
+ +
+

Metrics

+
--
Load (ms)
--
Latency (tok/s)
--
Memory (MB)
+
+ +
+

Viability Assessment

+
+Waiting for benchmark results...
+
+Target models:
+  Falcon-H1-Tiny-90M: ~45MB quantized (Q2_K)
+  Bonsai-1.7B: ~400MB quantized (Q4_0)
+
+Browser limits:
+  Chrome: 4GB WASM memory
+  Firefox: 2GB WASM memory
+  Safari: 1GB WASM memory (may fail on 1.7B)
+
+
+ + + + \ No newline at end of file