🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON APPLE
Run GPT-1 on Apple hardware
18 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| Apple M2 Ultra 192GB → | ~10,012.2 | yes | 2613k | ~$6,600 |
| Apple M2 Ultra 64GB → | ~10,012.2 | yes | 855k | ~$4,000 |
| Apple M1 Ultra 128GB → | ~10,012.2 | yes | 1734k | ~$4,800 |
| Apple M1 Ultra 64GB → | ~10,012.2 | yes | 855k | ~$3,700 |
| Apple M4 Max 64GB → | ~6,833.3 | yes | 855k | ~$3,900 |
| Apple M4 Max 36GB → | ~6,833.3 | yes | 470k | ~$3,000 |
| Apple M4 Max 128GB → | ~6,833.3 | yes | 1734k | ~$4,900 |
| Apple M4 Max 48GB → | ~6,833.3 | yes | 635k | ~$3,300 |
| Apple M1 Max 32GB → | ~5,006.1 | yes | 416k | ~$2,000 |
| Apple M3 Max 48GB → | ~5,006.1 | yes | 635k | ~$3,200 |
| Apple M3 Max 64GB → | ~5,006.1 | yes | 855k | ~$3,700 |
| Apple M3 Max 128GB → | ~5,006.1 | yes | 1734k | ~$4,700 |
| Apple M1 Max 64GB → | ~5,006.1 | yes | 855k | ~$2,600 |
| Apple M2 Max 32GB → | ~5,006.1 | yes | 416k | ~$2,200 |
| Apple M2 Max 64GB → | ~5,006.1 | yes | 855k | ~$2,800 |
| Apple M2 Max 96GB → | ~5,006.1 | yes | 1294k | ~$3,300 |
| Apple M3 Max 36GB → | ~3,754.6 | yes | 470k | ~$2,900 |
| NVIDIA GeForce RTX 2050 → | ~1,487.2 | yes | 75k | — |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Apple hardware runs GPT-1?▶
On GenAIList, 18 Apple options can run GPT-1 at Q4 — the fastest is the Apple M2 Ultra 192GB at ~10,012.2 tok/s.
How fast is GPT-1 on Apple hardware?▶
Estimated generation speed ranges from ~1,487.2 to ~10,012.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.