AI desktop
Apple Mac Studio (M5 Ultra, 512GB)
512 GB of unified memory · 1,200 GB/s
No recent in-stock listing. Check the manufacturer's product page ↗
We may earn a commission from retailer links. Affiliate disclosure
Where to buy
No listing has been checked in the last 72 hours. See the manufacturer for availability.
Some links are affiliate links. Prices change constantly, so confirm the exact configuration, condition, shipping, and final total at the retailer before buying.
Recorded catalog price
Price unconfirmed
Recorded . Not in stock at that check. Retailer offers above may differ by condition or configuration.
Specs
- Memory
- 512 GB
- Memory bandwidth
- 1200 GB/s
- FP16 compute
- Not published
- INT8 compute
- Not published
- Whole-machine power
- 480 W
- MSRP
- Not published
- Memory architecture
- Unified with the CPU
Fields marked "not published" are ones the vendor does not state. We leave them blank rather than estimate.
Board power covers the GPU card alone; whole-machine power covers the complete computer. A card's rating excludes the rest of the system. See our power, cooling, and noise guide for power-supply planning.
What it can run
Whether a model's weights fit in 512 GB, with a 20 percent allowance for the KV cache, activations, and the runtime. This is arithmetic on the quantization format, not a benchmark. Long contexts and large batches need more.
At Q4, the smallest format below, 24 of the 25 models we size fit on this machine.
| Model | Q4 (4-bit) ? | Q5 (5-bit) | Q8 (8-bit) | FP16 |
|---|---|---|---|---|
| Qwen3.5-0.8B (0.8B) | Fits | Fits | Fits | Fits |
| LFM2.5-1.2B-Thinking (1.17B) | Fits | Fits | Fits | Fits |
| Qwen3.5-2B (2B) | Fits | Fits | Fits | Fits |
| SmolLM3-3B (3B) | Fits | Fits | Fits | Fits |
| Qwen3.5-4B (4B) | Fits | Fits | Fits | Fits |
| Gemma 4 E4B (8B) | Fits | Fits | Fits | Fits |
| Qwen3-8B (8.2B) | Fits | Fits | Fits | Fits |
| Qwen3.5-9B (9B) | Fits | Fits | Fits | Fits |
| Gemma 4 12B (11.95B) | Fits | Fits | Fits | Fits |
| gpt-oss-20b (21B) | Fits | Fits | Fits | Fits |
| Mistral Small 3.2 24B (24B) | Fits | Fits | Fits | Fits |
| Gemma 4 26B-A4B (25.2B) | Fits | Fits | Fits | Fits |
| Gemma 3 27B (27B) | Fits | Fits | Fits | Fits |
| Qwen3.5-27B (27B) | Fits | Fits | Fits | Fits |
| Qwen3.8-27B (27B) | Fits | Fits | Fits | Fits |
| Gemma 4 31B (30.7B) | Fits | Fits | Fits | Fits |
| Qwen3.5-35B-A3B (35B) | Fits | Fits | Fits | Fits |
| Llama 3.3 70B Instruct (70B) | Fits | Fits | Fits | Fits |
| gpt-oss-120b (117B) | Fits | Fits | Fits | Fits |
| Qwen3.5-122B-A10B (122B) | Fits | Fits | Fits | Fits |
| Qwen3-235B-A22B (235B) | Fits | Fits | Fits | No |
| DeepSeek-V4-Flash-0731 (284B) | Fits | Fits | Fits | No |
| DeepSeek-V3 (671B) | Fits | Fits | No | No |
| GLM-5.1 (744B) | Fits | No | No | No |
| Kimi K3 (2800B) | No | No | No | No |
Related hardware
Closest memory capacity to this one, which is what decides whether the same models load.
- Apple Mac Studio (M3 Ultra, 512GB) — 512 GB
- Apple Mac Studio (M4 Max, 128GB) — 128 GB
- Apple Mac Studio (M5 Max, 128GB) — 128 GB
Sources
Every spec here is recorded from a vendor page we fetched. See our methodology for how prices and specs are sourced.
- Mac Studio - Technical Specifications — Apple , fetched
- Apple introduces new Mac Studio with M5 Max and M5 Ultra — Apple , fetched