HomeInstalled models

What runs on your premises. Not what tops a leaderboard.

Open models with downloadable weights, installed on the machine and updated quarterly. Every row was checked against the model card at its maker.

Collected
29.08.2026
Models
5
Refresh
quarterly

Open, installable, yours.

An open model stays on the machine after the service contract ends: that is what separates a downloaded weight from an API key.

Proof
ModelSizeGPU memoryContextLicenceMachines
Qwen 3.8 27BAlibaba · flagship27 B · dense≈ 56 Go (BF16)256 k tokensApache 2.0N1 · N2 · N4
GLM-5.3-FlashZ.ai320 B · 18 B actifs≈ 320 Go (BF16)256 k tokensMITN2 · N4
DeepSeek V4 FlashDeepSeek284 B · 13 B actifs≈ 291 Go (BF16)1 M tokensMITN4
Apertus 70BEPFL / ETH / CSCS · Suisse71 B · dense≈ 142 Go (BF16)131 k tokensApache 2.0N2 · N4
Apertus v1.5 8BEPFL / ETH / CSCS · Suisse9 B · dense≈ 18 Go (BF16)131 k tokensApache 2.0N1 · N2 · N4

The models that top the leaderboards do not fit in a building.

The “max” versions that top the leaderboards (Kimi K3: 2.8 trillion parameters, Qwen 3.8 Max, GLM-5.3) need clusters of several dozen cards and remain API services. They serve here as a level reference. What the machine installs is the catalogue above — the most powerful models an organisation can actually run inside its own walls.

Sources for the rankings quoted, collected on 29.08.2026 : LMArena, Artificial Analysis.