Written by Jakub Rusinowski · Last updated October 8, 2024
Yes
Yes — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB) (~11.5 GB spare), at ~8.3 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~8.3 tok/s
| Usable memory for models | 48 GB |
| Memory bandwidth | 546 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 66.7 GB | ✗ No | — | — | 64.6 GB |
| Q8_0 | 36.5 GB | ✓ Yes | 64K | ~8.3 tok/s | 34.3 GB |
| Q6_K | 28.6 GB | ✓ Yes | 64K | ~10.7 tok/s | 26.5 GB |
| Q5_K_M | 25 GB | ✓ Yes | 64K | ~12.2 tok/s | 22.9 GB |
| Q4_K_M | 21.6 GB | ✓ Yes | 64K | ~14.2 tok/s | 19.5 GB |
| Q3_K_M | 15.9 GB | ✓ Yes | 64K | ~19.5 tok/s | 13.8 GB |
| Q2_K | 12.8 GB | ✓ Yes | 64K | ~24.6 tok/s | 10.6 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Aya Expanse 32B | 21.6 GB | ✓ Fits | ~14.2 tok/s |
| Aya Expanse 8B | 6.7 GB | ✓ Fits | ~47.6 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB) (~11.5 GB spare), at ~8.3 tok/s (estimated), with room for about 65,536 tokens of context.
Q8_0 — it needs about 36.5 GB of the 48 GB available, downloads as roughly 34.3 GB, and runs at an estimated 8.3 tokens/sec with up to 64K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
← Can I Run It? | Aya Expanse model page | Check your hardware