HardwareRecommended

Framework Laptop 13 / 16

Repairable, modular laptop with strong Linux support. The right choice if you want a portable agent host that doubles as a daily driver.

Specs at a glance

CPUAMD Ryzen 7040 / 8040 / Intel Core Ultra
GPU / NPUIntegrated, optional discrete on FW16
RAM options8 / 16 / 32 / 64 GB DDR5
StorageNVMe SSD 500 GB to 4 TB
Power draw15-80 W
Form factor13.5" or 16" laptop
Local LLM capabilityUp to 13B Q4
Price point€1100-2200

Choosing between devices? The hardware buyer's guide compares them by budget, and Local LLM benchmarks has the published speeds, machine by machine.

Overview

Framework laptops earn their place in this guide because they're the rare modern laptop where repair, upgrade and Linux support are first-class. The 13-inch with 32 GB RAM runs Hermes Agent comfortably alongside browser-tool workloads. The 16-inch with discrete GPU adds local LLM headroom. Neither is the right pick for always-on agent hosting (you want a fanless mini PC for that), but as a portable AI development machine that lasts five years, Framework is the most credible option.

Best for

  • Engineers who want one machine for both work and agent hosting
  • Linux-first deployments
  • Repair-friendly hardware

Not for

  • Always-on hosting (laptop ≠ server)
  • Strict per-watt efficiency vs Mac Mini
  • Cost-optimised setups (mini PC + dedicated laptop is cheaper)

Compatible self-hosted agents

Listed as compatible with Framework Laptop 13 / 16 from each agent's requirements, not from a test (with the caveats from “Best for” / “Not for” above):

Hermes Agent
No sandbox by default · MIT
OpenClaw
No sandbox by default · MIT
Nanobot
No sandbox by default · MIT
ZeroClaw
Sandbox on by default · MIT or Apache-2.0

Where to buy

Manufacturer page: https://frame.work. We don't have an active affiliate programme with this vendor: see our disclosure page for the full list of partners we do work with.


See also: all AI hardware · AI agents tracker · AI CVEs · edge AI hardware buyer's guide · scan your AI stack · our methodology.