# Hardware

> CPU and GPU support, what has been verified on the GPU, and how Kjarni runs in the browser.

Source: https://kjarni.ai/docs/hardware/ (published 2026-10-30)

Everything runs on CPU by default, using all physical cores within a call, with SIMD
kernels for x86-64 (AVX2) and ARM (NEON), and int4/int8 quantized weights for chat models.

GPU support goes through WebGPU (the `wgpu` library), so it uses Vulkan, DirectX 12 or
Metal and works on AMD, Intel, Apple and NVIDIA hardware without a CUDA toolkit. Pass
`gpu: true` (or `--gpu`, or `device: "gpu"` depending on the binding).

| Model type | GPU status |
|---|---|
| Encoders: embeddings, classification, reranking | Output matches PyTorch, within 6e-6 |
| Chat and generation | Full-precision Qwen matches PyTorch; quantized files can produce different text on the GPU than on the CPU |
| Speech to text: Whisper, from 0.2.8 | Same transcript as the CPU on the `whisper-small` test clips |
| Summarization and translation | Less tested; prefer CPU |

The GPU is not the fastest option on an NVIDIA card: CUDA engines are well ahead on the same hardware, as [the benchmarks](https://github.com/olafurjohannsson/kjarni/blob/main/bench/BENCHMARKS.md) show. What it adds is that one build runs on any vendor's GPU with nothing else to install.

In the browser, `kjarni-wasm` runs on CPU with WebAssembly SIMD, in a Web Worker so the
page does not freeze. A WebGPU build of the engine exists in the repository but is not in
the npm package yet.