Can my PC run this LLM?
Type your GPU or Mac chip — see the models that actually run, their quant, the memory they need and an estimated tok/s band.
Popular picks
How it works
- Memory: weights + KV cache + compute buffer against what your GPU (or unified memory) can actually use.
- Speed: a memory-bandwidth model calibrated against 52 public benchmarks.
- Every number carries a band and a confidence label — measured, calibrated or theoretical.
Every number on this site ships with an error band and a confidence label: measured, calibrated (±12% for NVIDIA and AMD GPUs running a dense model fully on the GPU, ±20% otherwise), or theoretical (±30%).
Popular GPUs and Macs
- GeForce RTX 5090
- GeForce RTX 5080
- GeForce RTX 5070 Ti
- GeForce RTX 5070
- GeForce RTX 5060 Ti 16GB
- GeForce RTX 5060
- GeForce RTX 4090
- GeForce RTX 4070
- GeForce RTX 4060
- GeForce RTX 3090
- GeForce RTX 3060 12GB
- Radeon RX 9070 XT
- Radeon RX 9060 XT 16GB
- Radeon RX 7900 XTX
- GeForce RTX 4060 Laptop
- Apple M4
- Apple M4 Pro
- Apple M4 Max (40-core GPU)
- Apple M5
- Apple M5 Pro
- Apple M5 Max (40-core GPU)
- Ryzen AI Max+ 395 (Strix Halo)
- DDR5-5600 dual-channel CPU