AMD SMI vs Glances
AMD SMI
rocm.docs.amd.comGlances
nicolargo.github.ioSide by side
| Figure | AMD SMI | Glances |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Web | — | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| Android | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 2 |
| Spec score · Hardware Monitoring Software | 8.1 (#19) | 8.9 (#6) |
| Spec score · Hardware monitoring tools | 7.7 (#39) | 8.6 (#12) |
| Installation | AMD SMI is included with most Linux ROCm Core SDK installations and can also be installed as the standalone amdrocm-amdsmi package. | The documented installation paths include pip, pipx, uvx, operating-system packages, and optional extras such as web or all. |
| Requirements | The GPU path requires the amdgpu-dkms driver; CPU discovery and CPU commands require amd_hsmp or hsmp_acpi, and Python and the CLI require 64-bit Python 3.6.8 or later. | Glances 4 requires Python 3.10 or higher; version 4 and higher do not support Python 2 or Python earlier than 3.10. |
Plans
In their own words
Glances
Glances is a free, open-source, cross-platform tool for monitoring real-time system statistics and running processes. Its listed coverage includes CPU, memory, load, processes, network, disk I/O, sensors, filesystems, containers, alerts, and uptime. Client/server mode enables remote monitoring through a terminal, web interface, or API, while its built-in web UI lets users view a system from a browser-equipped device. Statistics can be exported to CSV or JSON files, databases such as InfluxDB and Prometheus, brokers such as RabbitMQ and Kafka, or a REST endpoint. The project documents Docker and Podman support and describes Docker and LXC container monitoring in its README. Installation options include pip, pipx, Homebrew, Linux and FreeBSD packages, and Docker images. Glances 4 requires Python 3.10 or higher. Its default installation does not include web interface dependencies; separate extras cover features such as web, GPU, containers, exports, and MCP. Version 4.5.1 and higher can provide an MCP server for AI assistants. The project uses the LGPL version 3 license.