List your company

LLM Inference on WebLLM Windows 11 RTX PRO 2000 Blackwell 8GB

51.1Decode Throughput (tok/s)Qwen2.5-0.5B
7.4218.7630.141.44Feb 9, 2026

Evaluation results

MethodLinks
Qwen2.5-0.5BBrowser=Chrome 144, Backend=D3D12, Quantization=q4f162026.0251.1650
Qwen2.5-1.5BBrowser=Chrome 144, Backend=D3D12, Quantization=q4f162026.0245.7350
Qwen2.5-0.5BBrowser=Firefox 147, Backend=D3D12, Quantization=q4f162026.029.173
Qwen2.5-1.5BBrowser=Firefox 147, Backend=D3D12, Quantization=q4f162026.029.155