Can an Apple M3 Max 36GB run GPT OSS 120B?
No
No. It needs 66.18 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
GPT OSS 120B has 116.83 billion parameters across 36 layers, of which 5.7 billion are read for each token. The Apple M3 Max 36GB has 36 GB of unified memory at 400 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 | 116.09 GB | no | — |
| Q6_K | 89.71 GB | no | — |
| Q5_K_M | 77.87 GB | no | — |
| Q4_K_M | 66.18 GB | no | — |
| IQ4_XS | 58.29 GB | no | — |
| Q3_K_M | 53.67 GB | no | — |
| IQ3_XXS degraded | 42.1 GB | no | — |
| Q2_K degraded | 46.05 GB | no | — |
| IQ2_XXS degraded | 28.5 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 M3 Max 36GB, at a quantisation worth using:
- GPT OSS 20B — 20.91B at Q8_0, 21.17 GB, about 75.3 tokens/s
Shortening the context window will not rescue this one: at 4k it still wants 66.09 GB against 66.18 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 GPT OSS 120B at a quantisation worth using is the Ryzen AI Max+ 395 96GB, around $1,999 for the whole machine, running it at Q4_K_M at about 51.8 tokens per second. Check the current price (affiliate link; indicative price reviewed 2026-09-01). Compare every option.
Keep going
Everything the Apple M3 Max 36GB runs, the full breakdown for GPT OSS 120B, or check a different pairing in the calculator.