Editing a copy of Mac Studio M3 Ultra 512GB
Choose parts or a complete machine. Compatibility, the total and what it runs update as you go, and nothing is saved until you share it.
A complete machine needs no part checks.
Best fit:DeepSeek V4 FlashMXFP4at 32k, 23 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| Machine | Mac Studio M3 Ultra 512GB 512 GB unified · 819 GB/s | $23,000 | Buy | |
| Total | $23,000 | Prices checked 2 h ago | ||
What this build runs
The most precise quant that fits, for every model in the catalogue. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | MXFP4 | fits | 148.8 GB | 1024k | 23tok/sest. | 84 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | Q8_0 | fits | 318.8 GB | 1024k | 12tok/sest. | 113 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q8_0 | fits | 176.9 GB | 256k | 5tok/sest. | 88 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.0 GB | 256k | 17tok/sest. | 181 tok/s | chat |
| MiniMax M2.7 MiniMax | Q8_0 | fits | 235.0 GB | 200k | 16tok/sest. | 238 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q8_0 | fits | 122.6 GB | 256k | 28tok/sest. | 424 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 17tok/sest. | 181 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | fits | 61.0 GB | 128k | 74tok/sest. | 684 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.6 GB | 256k | 64tok/sest. | 1021 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q8_0 | fits | 120.8 GB | 256k | 25tok/sest. | 428 tok/s | chat, coding, long documents |
$23,000
1 item