Can an Apple M3 Max 36GB run GPT OSS 120B?
No
It needs 59.65 GB at MXFP4 against the 25.2 GB this device makes available, and there is not enough system memory to bridge the gap.
In practice
No. At MXFP4 GPT OSS 120B needs 59.65 GB and the Apple M3 Max 36GB makes 25.2 GB available, and there is not enough system memory to bridge the difference at a speed worth having.
Settings will not close a gap this size: at a 4k window it still needs 59.51 GB, because the weights, not the cache, are what fill the card. The honest options are a smaller model, which the next section lists, or hardware with more memory.
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.
| Quantization | Total needed | Fits | Speed |
|---|---|---|---|
| MXFP4 | 59.65 GB | no | n/a |
Nothing on this ladder fits entirely, including the 2-bit levels we do not recommend. This model is published in a single native format, so every row is the same file.
What to run instead
A smaller model from the same family is the straightforward answer. These fit on an Apple M3 Max 36GB at a quantization worth using:
- GPT OSS 20B, 20.91B at MXFP4, 11.81 GB, about 66.0 tokens/s
Shortening the context will not rescue this one: at 4k it still wants 59.51 GB against 59.65 GB at 8k, because the weights, not the cache, are what fill the card.
Models of this size are what a second GPU or a large-memory machine is for. The multi-GPU guide shows what 2 cards add, and the Mac and PC comparison shows where unified memory holds a model that no single card can.
Or the hardware that does run it
The cheapest device we track that runs GPT OSS 120B at a quantization worth using is the GeForce GTX 1660 SUPER, around $110 used , running it at MXFP4 at about 15.4 tokens per second. Check the current price (affiliate link, indicative price reviewed 2026-09-01). Compare every option.
What else an Apple M3 Max 36GB runs well
For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.
| Model | Quantization | Memory | Speed |
|---|---|---|---|
| Gemma 4 12B Instruct | Q8_0 | 13.52 GB | 20.7 t/s |
| GPT OSS 20B | MXFP4 | 11.81 GB | 66.0 t/s |
| Qwen3 14B | Q8_0 | 16.28 GB | 18.0 t/s |
| Qwen3.5 9B | Q8_0 | 10.22 GB | 30.8 t/s |
The same model on nearby hardware
Memory decides whether GPT OSS 120B loads and bandwidth decides how quickly it answers. Here is what a step down, a card with the same memory and a step up do with it.
| Device | Memory | Bandwidth | Result |
|---|---|---|---|
| GeForce RTX 5090 | 32 GB | 1792 GB/s | partial, 31.2 t/s |
| Apple M4 Pro 48GB | 48 GB | 273 GB/s | does not fit |
Questions people ask
How much VRAM does GPT OSS 120B need on Apple M3 Max 36GB?
At MXFP4 with an 8k context window it needs 59.65 GB in total: 59.03 GB of weights, 0.29 GB of KV cache and 0.34 GB of runtime overhead. The Apple M3 Max 36GB makes about 25.2 GB available once the operating system has taken its share.
What should I run instead of GPT OSS 120B on Apple M3 Max 36GB?
GPT OSS 20B fits at MXFP4 and runs at about 66.0 tokens per second. Smaller models from the same family are the usual answer.
Keep going
Everything the Apple M3 Max 36GB runs, the full breakdown for GPT OSS 120B, how the numbers are made in the methodology, or a different pairing in the calculator.