🔌
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 Transformer (Adaptive Input Embeddings) WT103 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 → | ~4,742.6 | yes | 2612k | ~$6,600 |
| Apple M2 Ultra 64GB → | ~4,742.6 | yes | 854k | ~$4,000 |
| Apple M1 Ultra 128GB → | ~4,742.6 | yes | 1733k | ~$4,800 |
| Apple M1 Ultra 64GB → | ~4,742.6 | yes | 854k | ~$3,700 |
| Apple M4 Max 64GB → | ~3,236.8 | yes | 854k | ~$3,900 |
| Apple M4 Max 36GB → | ~3,236.8 | yes | 469k | ~$3,000 |
| Apple M4 Max 128GB → | ~3,236.8 | yes | 1733k | ~$4,900 |
| Apple M4 Max 48GB → | ~3,236.8 | yes | 634k | ~$3,300 |
| Apple M1 Max 32GB → | ~2,371.3 | yes | 414k | ~$2,000 |
| Apple M3 Max 48GB → | ~2,371.3 | yes | 634k | ~$3,200 |
| Apple M3 Max 64GB → | ~2,371.3 | yes | 854k | ~$3,700 |
| Apple M3 Max 128GB → | ~2,371.3 | yes | 1733k | ~$4,700 |
| Apple M1 Max 64GB → | ~2,371.3 | yes | 854k | ~$2,600 |
| Apple M2 Max 32GB → | ~2,371.3 | yes | 414k | ~$2,200 |
| Apple M2 Max 64GB → | ~2,371.3 | yes | 854k | ~$2,800 |
| Apple M2 Max 96GB → | ~2,371.3 | yes | 1293k | ~$3,300 |
| Apple M3 Max 36GB → | ~1,778.5 | yes | 469k | ~$2,900 |
| NVIDIA GeForce RTX 2050 → | ~704.5 | yes | 74k | — |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Apple hardware runs Transformer (Adaptive Input Embeddings) WT103?▶
On GenAIList, 18 Apple options can run Transformer (Adaptive Input Embeddings) WT103 at Q4 — the fastest is the Apple M2 Ultra 192GB at ~4,742.6 tok/s.
How fast is Transformer (Adaptive Input Embeddings) WT103 on Apple hardware?▶
Estimated generation speed ranges from ~704.5 to ~4,742.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.