wllama v4.0.0: llama.cpp in the browser, up to 2.8x faster with WebGPU hybrid
ngxson · x · 2026-11-23
wllama, a WebAssembly binding for llama.cpp (1.4k stars), shipped v4.0.0: up to 2.8x faster prefill and loading and 2.5x faster generation on Chrome, no more 4GB size limit (a 5.15GB Gemma 4 E4B now runs at 56 t/s prefill), hybrid CPU + WebGPU inference on Chrome and Firefox for bigger models, plus video input, full-duplex realtime audio, LoRA adapters and speculative decoding (MTP, DFlash, Eagle3). MIT-licensed with an online demo.
Related event: wllama v4.0.0 Boosts In-Browser LLM Inference Up to 2.8x(4 posts)→
More from Infra
- KV cache offload to RAM runs Qwen 3.8 with 8x200k streams on 4x3090 — Mr_Moonsilver · 2026-11-23
- OpenAI chart reveals unreleased GPT-6 Astra models; Domingos questions billions for <0.3 bits — pmddomingos · 2026-11-23
- wllama author: RPC-linked wasm instances show little performance loss, credits GGML RPC backend — ngxson · 2026-11-23
- layerpool open-sources layer-split fine-tuning across machines with unchanged HF Trainer — Historical_Syrup_461 · 2026-11-23
- wllama v4.0.0 ships: in-browser llama.cpp up to 2.8x faster with WebGPU hybrid — ngxson · 2026-11-23
- French dev laments missed chance to build green data center ecosystem on low-carbon grid — Dimillian · 2026-11-23