š LLM Engine Comparison
WebLLM vs Transformers.js ā¢ Same Model, Fair Comparison
GPU
Detecting...
WebGPU
Detecting...
CPU Cores
-
Model:
Qwen 3 0.6B (WebLLM only)
Qwen 3 1.7B (WebLLM only)
Qwen 3 4B (WebLLM only)
Gemma 3 1B Instruct
Gemma 3 4B Instruct (WebLLM only)
Llama 3.2 1B Instruct
Llama 3.2 3B Instruct (WebLLM only)
SmolLM2 360M Instruct
Qwen 2.5 0.5B Instruct
Phi 3.5 Mini 3.8B (WebLLM only)
Iterations:
Max Tokens:
ā¶ļø Run Comparison
Ready
Selected:
Gemma 3 1B Instruct
Both Engines
š Results
š Log
Ready...