Mac Studio M5 Ultra
Complete box · $5,499/96GB · $9,499/256GB · 512GB late Oct, price TBD (~$13.5k est)
AppleComplete system$13,500 (estimated) · Aug 31, 2026View on Amazonpaid link
- Memory
- 512 GB~384 GB usable
- Bandwidth
- 1.2kGB/s — sets decode speed
- Compute
- 60FP16 TFLOPS — sets prefill
- Power
- 270 Wunder sustained load
- Noise
- 35 dBAdesk-friendly
- Price per GB
- $26of accelerator memory
Price history
tracking
Tracking since 2026-08-31 — not enough history for a trend yet.
1 observation recorded · Last checked 2026-08-31. Check the retailer before acting on this — we would rather say the data is old than pretend otherwise.
What it can run
5 of 6 reference workloads fit. The largest is 320B MoE A18B · FP8 (frontier-ish), at an estimated 28 tok/s of single-stream decode — the fastest of the 2 machines here that can run it.
| Workload | Needs | Fits | Prefill t/s | Decode t/s | Batched t/s | $ per t/s |
|---|---|---|---|---|---|---|
8B dense · Q4 (chat, drafts) dense · 4.7 GB read per token | 5.4 GB | Yes | 563 | 166 | 404 | $81 |
32B dense · Q4 (coding) dense · 19 GB read per token | 21.8 GB | Yes | 141 | 41 | 101 | $329 |
70B dense · Q4 (strong general) dense · 40 GB read per token | 46 GB | Yes | 64 | 20 | 46 | $675 |
120B MoE A5B · MXFP4 (gpt-oss class) MoE · 2.9 GB read per token | 72.4 GB | Yes | 882 | 174 | 599 | $78 |
320B MoE A18B · FP8 (frontier-ish) MoE · 18 GB read per token | 368 GB | Yes | 250 | 28 | 146 | $482 |
671B MoE A37B · Q4 (DeepSeek class) MoE · 18.5 GB read per token | 437 GB | No | 122 | 27 | 84 | — |
Figures are modelled from this machine's bandwidth and compute, not measured on one. How they are derived →
Alternatives that also run 320B MoE A18B · FP8 (frontier-ish)
| Machine | Price | Memory | Decode t/s | $ per t/s |
|---|---|---|---|---|
Mac Studio M5 Ultra — this machine | $13,500 | 512 GB | 28 | $482 |
| $9,499 | 512 GB | 19 | $500 |