Can an Apple M4 16GB run DeepSeek V4 Flash 0731?
No
No. It needs 171.6 GB at four-bit precision against the 10.72 GB this device makes available, and there is not enough system memory to make up the difference.
The numbers
DeepSeek V4 Flash 0731 has 304.18 billion parameters across 43 layers, of which 20.36 billion are read for each token. The Apple M4 16GB has 16 GB of unified memory at 120 GB/s, of which about 10.72 GB is left for a model once the operating system has taken its share.
| Quantisation | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 301.56 GB | no | — |
| Q6_K | 232.86 GB | no | — |
| Q5_K_M | 202.05 GB | no | — |
| Q4_K_M | 171.6 GB | no | — |
| IQ4_XS | 151.06 GB | no | — |
| Q3_K_M | 139.02 GB | no | — |
| IQ3_XXS degraded | 108.92 GB | no | — |
| Q2_K degraded | 119.19 GB | no | — |
| IQ2_XXS degraded | 73.51 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 16GB, at a quantisation worth using:
- DeepSeek Coder V2 Lite Instruct — 15.71B at Q4_K_M, 9.5 GB, about 52.6 tokens/s
- DeepSeek Coder 7B Instruct V1.5 — 6.91B at Q6_K, 9.58 GB, about 10.4 tokens/s
- DeepSeek Coder 6.7B Instruct — 6.74B at Q6_K, 9.7 GB, about 10.2 tokens/s
Shortening the context window will not rescue this one: at 4k it still wants 171.47 GB against 171.6 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 V4 Flash 0731 at a quantisation worth using is the Apple M3 Ultra 256GB, around $5,599 for the whole machine, running it at Q4_K_M at about 55.8 tokens per second. Check the current price (affiliate link; indicative price reviewed 2026-09-01). Compare every option.
Keep going
Everything the Apple M4 16GB runs, the full breakdown for DeepSeek V4 Flash 0731, or check a different pairing in the calculator.