Mac Studio M2 Ultra 76-core GPU, 192 GB
| GPU(s) | Apple M2 Ultra 76-core GPU |
|---|---|
| VRAM / unified memory (GB) | 192 |
| CPU | Apple M2 Ultra (16+8 CPU) |
| Motherboard | |
| RAM | 192 GB unified |
| PSU | |
| Other | |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Llama 2 7B | Q4_0 | llama.cpp Metal (FA, Aug 2026 build) | 125.21 |
| gpt-oss 20B | MXFP4 | llama.cpp | 116.08 |
| gpt-oss 120B | MXFP4 | llama.cpp | 79.68 |
Source: https://github.com/ggml-org/llama.cpp/discussions/4167
https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inference
https://github.com/ggml-org/llama.cpp/discussions/15396
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 M2 Ultra run gpt-oss 120B? · Can Apple M2 Ultra run gpt-oss 20B?