Can an Apple M4 Max 36GB run DeepSeek R1?
No
No. It needs 386.18 GB at four-bit precision against the 25.2 GB this device makes available, and there is not enough system memory to make up the difference.
The numbers
DeepSeek R1 has 684.53 billion parameters across 61 layers, of which 38.57 billion are read for each token. The Apple M4 Max 36GB has 36 GB of unified memory at 546 GB/s, of which about 25.2 GB is left for a model once the operating system has taken its share.
| Quantisation | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 678.64 GB | no | — |
| Q6_K | 524.04 GB | no | — |
| Q5_K_M | 454.71 GB | no | — |
| Q4_K_M | 386.18 GB | no | — |
| IQ4_XS | 339.96 GB | no | — |
| Q3_K_M | 312.86 GB | no | — |
| IQ3_XXS degraded | 245.13 GB | no | — |
| Q2_K degraded | 268.24 GB | no | — |
| IQ2_XXS degraded | 165.44 GB | no | — |
Nothing on this ladder fits, including the two-bit levels we do not recommend.
What to do instead
The straightforward answer is a smaller model from the same family. These do fit on a Apple M4 Max 36GB, at a quantisation worth using:
- DeepSeek Coder V2 Lite Instruct — 15.71B at Q8_0, 16.21 GB, about 144.4 tokens/s
- DeepSeek Coder 7B Instruct V1.5 — 6.91B at Q8_0, 11.14 GB, about 40.2 tokens/s
- DeepSeek Coder 6.7B Instruct — 6.74B at Q8_0, 11.22 GB, about 39.9 tokens/s
Shortening the context window will not rescue this one: at 4k it still wants 385.69 GB against 386.18 GB at 8k, because the weights rather than the cache are what fill the card. The gap here is too large for settings to close.
Or the hardware that does run it
The cheapest device we track that runs DeepSeek R1 at a quantisation worth using is the Apple M3 Ultra 512GB, around $9,499 for the whole machine, running it at IQ4_XS at about 32.6 tokens per second. Check the current price (affiliate link; indicative price reviewed 2026-09-01). Compare every option.
Keep going
Everything the Apple M4 Max 36GB runs, the full breakdown for DeepSeek R1, or check a different pairing in the calculator.