# System Requirements

> What your machine needs to run MiniMax Converter — the minimum that gets you going, and what we recommend for the smoothest experience.

Back to [home](https://minimax-converter.com/index.md).

## Minimum (runs the app)

| | |
|---|---|
| **OS** | Windows 10 (1809+), macOS 11 Big Sur, or any current Linux distribution (Ubuntu 22.04+, Debian 12+, Fedora, Arch, etc.) |
| **CPU** | 64-bit dual-core processor (x86_64 or Apple Silicon ARM64) with AVX support — most CPUs from 2012 onwards qualify |
| **RAM** | 4 GB |
| **Disk** | 2 GB free for the app and any AI models you choose to download |
| **GPU** | Not required — every feature has a CPU fallback |
| **Display** | 1280 × 720 |
| **Network** | Only for the first download and to fetch optional AI models the first time you use them. After that, conversions run fully offline. |

## Recommended (smooth & fast)

| | |
|---|---|
| **OS** | Windows 11, macOS 14 Sonoma or later, or a current Linux distribution (Ubuntu 24.04, Fedora 40+, etc.) |
| **CPU** | Quad-core or better. 8+ cores really shines for parallel audio batch conversion (one file per core). |
| **RAM** | 8 GB. Bump to 16 GB if you transcribe long videos, upscale 4K photos, or run several conversions in parallel. |
| **Disk** | 5 GB free. Leaves headroom for AI models, cached working files, and large source media. |
| **GPU** | Any modern GPU helps. NVIDIA RTX 20-series or newer accelerates Whisper transcription via CUDA; AMD / Intel / older NVIDIA accelerate via Vulkan; Apple Silicon uses the Neural Engine via Core ML. |
| **Display** | 1440 × 900 or larger |
| **Network** | Same as minimum — only used for the initial download and first-time AI model fetches. |

## What scales with hardware

Most file conversions run anywhere. The features below are the ones where better hardware makes a visible difference.

- **Whisper transcription (Subtitles / Lyrics)** — Apple Silicon (Core ML), NVIDIA (CUDA), AMD/Intel (Vulkan), or CPU. Typical speed-up over CPU: 3× on a recent MacBook M-series, 5–10× on a modern dGPU.
- **AI image upscaling (Real-ESRGAN)** — any Vulkan-capable GPU helps. CPU fallback works but is slow on 4K images.
- **Background removal (rembg / U2Net)** — runs on CPU comfortably; an NVIDIA GPU through onnxruntime-gpu speeds it up.
- **Parallel audio batch conversion** — scales with core count (uses cores − 2 to keep the OS responsive). On a 16-core machine: 14 simultaneous ffmpeg processes.
- **Hardware video encoding** — NVENC (NVIDIA), AMF (AMD), QSV (Intel), VAAPI (Linux), VideoToolbox (macOS). Faster than libx264 software encoding for H.264 targets, with auto-fallback to libx264 if the GPU encoder fails.

## Not supported

- 32-bit operating systems
- Windows 7, 8, and 8.1
- macOS 10.15 Catalina and earlier
- CPUs without AVX (pre-2012 Intel Atom, very old AMD)
- ARM Windows
- Mobile (Android, iOS)

## Related markdown

- [Help / User guide](https://minimax-converter.com/help/index.md)
- [Changelog](https://minimax-converter.com/changelog/index.md)
- [Landing page](https://minimax-converter.com/index.md)