Mac Studio M3 Ultra 512GB: Qwen3.8 27B and Mistral Medium 3.5 (Apple MLX benchmark)
| GPU(s) | Apple M3 Ultra (unified) |
|---|---|
| VRAM / unified memory (GB) | 512 |
| CPU | Apple M3 Ultra |
| Motherboard | |
| RAM | |
| PSU | |
| Other | |
| Reported total cost | |
| Power | Peak ~200 W (Apple, 65K-token context) |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Qwen3.8 27B | BF16, 8,192-token context | MLX (mlx_lm.benchmark) | 12.46 |
| Mistral Medium 3.5 128B | FP8, 8,192-token context | MLX (mlx_lm.benchmark) | 4.95 |
Apple Machine Learning Research, 15 Oct 2026, previous-generation baseline. Decode speed over 128 generated tokens after an 8,192-token context, single user.
Source: https://machinelearning.apple.com/research/mlx-distributed-inference
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
Quick answers: Can Apple M3 Ultra run Mistral Medium 3.5 128B? · Can Apple M3 Ultra run Qwen3.8 27B?