FitMyModel

Can it run? Every model and card we cover

Last updated

One page for each ranked open model on each device we list where the model fits in GPU memory. Fit uses the Ollama download size and the device's GPU memory; the headroom bands are our estimate. Pick your memory size in What fits my memory.

By memory size: 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · 48 GB · 64 GB · 96 GB · 128 GB

Devices: Arc B580 (12 GB for the GPU) · RTX 5060 Ti 16GB (16 GB for the GPU) · Arc Pro B60 (24 GB for the GPU) · Radeon AI Pro R9700 (32 GB for the GPU) · Ryzen AI Max+ 395 (64 GB) (48 GB for the GPU) · Ryzen AI Max+ 395 (128 GB) (96 GB for the GPU)

Gemma 4 31B (19–20 GB)

Gemma 4 26B-A4B (MoE) (16 GB)

Qwen3.8 27B (18 GB)

Qwen3.5 122B-A10B (MoE) (81 GB)

Nemotron 3.5 Super 120B-A12B (90 GB)

Qwen3.5 27B (17–20 GB)

Qwen3.5 35B-A3B (MoE) (22 GB)

Mistral Small 3.2 24B (15 GB)

gpt-oss 120B (65 GB)

Llama 3.3 70B (43 GB)

gpt-oss 20B (14 GB)

Phi-4 14B (9.1 GB)

Llama 3.1 8B (4.9 GB)