whichLlmmodel
Hardware Directory

Local AI Hardware Compatibility

Select your graphics card VRAM size or MacBook memory capacity to see exactly which open-source model quantizations run on your local hardware.

Dedicated GPUs (NVIDIA & AMD)

8GB VRAM GPUs

8GB VRAM

Budget and entry-level graphics cards with 8GB dedicated VRAM.

Common Graphics Cards:
NVIDIA RTX 4060NVIDIA RTX 3070NVIDIA RTX 3060 TiAMD RX 7600

12GB VRAM GPUs

12GB VRAM

Mid-range graphics cards with 12GB dedicated VRAM.

Common Graphics Cards:
NVIDIA RTX 3060 12GBNVIDIA RTX 4070NVIDIA RTX 4070 SuperAMD RX 6700 XT

16GB VRAM GPUs

16GB VRAM

High-end graphics cards with 16GB dedicated VRAM.

Common Graphics Cards:
NVIDIA RTX 4080NVIDIA RTX 4060 Ti 16GBAMD RX 7800 XT

24GB VRAM GPUs

24GB VRAM

Premium gaming and consumer graphics cards with 24GB dedicated VRAM.

Common Graphics Cards:
NVIDIA RTX 3090NVIDIA RTX 4090AMD RX 7900 XTX

32GB VRAM GPUs

32GB VRAM

Enterprise workstations and multi-GPU configurations with 32GB VRAM.

Common Graphics Cards:
NVIDIA RTX 5000 Ada (32GB)Dual NVIDIA RTX 4080 (32GB)Dual NVIDIA RTX 3080 16GB

Apple Silicon MacBooks (Unified Memory)

Macbook 16GB Unified Memory

16GB RAM

Apple Silicon Macs with 16GB of Unified Memory (~12GB VRAM allocation limit).

Supported Devices:
Apple M1/M2/M3 Macbook Pro (16GB)Apple M1/M2/M3 Macbook Air (16GB)

Macbook 24GB Unified Memory

24GB RAM

Apple Silicon Macs with 24GB of Unified Memory (~18GB VRAM allocation limit).

Supported Devices:
Apple M2/M3 Macbook Pro (24GB)Apple M2/M3 Macbook Air (24GB)

Macbook 36GB Unified Memory

36GB RAM

Apple Silicon Macs with 36GB of Unified Memory (~27GB VRAM allocation limit).

Supported Devices:
Apple M3 Pro Macbook Pro (36GB)