wllama v4.0.0 ships: in-browser llama.cpp up to 2.8x faster with WebGPU hybrid

ngxson · x · 2026-11-23

ngxson released wllama v4.0.0, the WebAssembly binding for llama.cpp: up to 2.8x faster prefill and loading, 2.5x faster generation on Chrome (vs v3.13.0, Apple M5 Max), hybrid CPU + WebGPU on Chrome/Firefox enabling bigger models, no 4GB GGUF size cap, LoRA adapters, speculative decoding (MTP/DFlash/Eagle3), video input and full-duplex realtime audio. MIT-licensed, demo available.

Related event: wllama v4.0.0 Boosts In-Browser LLM Inference Up to 2.8x(4 posts)→

Original post →

More from Infra

Infra channel →