🔌
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 Llama 3.2 90B on Apple hardware
11 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| Apple M2 Ultra 192GB → | ~13.2 | yes | 371k | ~$6,600 |
| Apple M2 Ultra 64GB → | ~13.2 | yes | 20k | ~$4,000 |
| Apple M1 Ultra 128GB → | ~13.2 | yes | 196k | ~$4,800 |
| Apple M1 Ultra 64GB → | ~13.2 | yes | 20k | ~$3,700 |
| Apple M4 Max 64GB → | ~9 | yes | 20k | ~$3,900 |
| Apple M4 Max 128GB → | ~9 | yes | 196k | ~$4,900 |
| Apple M3 Max 64GB → | ~6.6 | yes | 20k | ~$3,700 |
| Apple M3 Max 128GB → | ~6.6 | yes | 196k | ~$4,700 |
| Apple M1 Max 64GB → | ~6.6 | yes | 20k | ~$2,600 |
| Apple M2 Max 64GB → | ~6.6 | yes | 20k | ~$2,800 |
| Apple M2 Max 96GB → | ~6.6 | yes | 108k | ~$3,300 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Apple hardware runs Llama 3.2 90B?▶
On GenAIList, 11 Apple options can run Llama 3.2 90B at Q4 — the fastest is the Apple M2 Ultra 192GB at ~13.2 tok/s.
How fast is Llama 3.2 90B on Apple hardware?▶
Estimated generation speed ranges from ~6.6 to ~13.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.