Editing a copy of Mac Studio M4 Max 128GB
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 FlashUD-Q2_K_XLat 32k, 22 tok/sest.
| Component | Selection | Price | Where | Actions |
|---|---|---|---|---|
| Machine | Mac Studio M4 Max 128GB 128 GB unified · 546 GB/s | $4,999 | Buy | |
| Total | $4,999 | 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 | UD-Q2_K_XL | fits | 93.7 GB | 58k103k with q8 cache | 22tok/sest. | 49 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 85.4 GB | 256k | 7tok/sest. | 51 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 78.7 GB | 101k187k with q8 cache | 18tok/sest. | 138 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.0 GB | 256k | 11tok/sest. | 104 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 95.8 GB | 40k64k with q8 cache | 24tok/sest. | 245 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 12tok/sest. | 104 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 61.0 GB | 128k | 49tok/sest. | 395 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.6 GB | 256k | 43tok/sest. | 589 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 91.2 GB | 256k | 22tok/sest. | 247 tok/s | chat, coding |
| Gemma 4 31B | Q8_0 | fits | 34.5 GB | 256k | 10tok/sest. | 93 tok/s | – |
$4,999
1 item