Can the Apple M3 Max (64GB) run Llama 3.1 70B?
Yes
QuantQ4_K_MGood, most popular
Memory46.1 GBof 48 GB
Speed~6tokens/s
Yes. The Apple M3 Max (64GB) can run Llama 3.1 70B fully in unified memory at Q4_K_M (good, most popular), using about 46.1 GB of the 48 GB available, at roughly 6 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context. macOS lets the GPU use about 48 GB of the 64 GB unified memory by default.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 144.5 GB | Too big | — |
| Q8_0 | Near-lossless | 78.3 GB | Too big | — |
| Q6_K | Excellent | 61.2 GB | Too big | — |
| Q5_K_M | Very good | 53.5 GB | Too big | — |
| Q4_K_M | Good, most popular | 46.1 GB | Fits | ~6 tok/s |
| Q3_K_M | Noticeably degraded | 37.8 GB | Fits | ~7 tok/s |
| Q2_K | Heavily degraded | 29.8 GB | Fits | ~9 tok/s |
How to run Llama 3.1 70B on the Apple M3 Max (64GB)
With Ollama installed, one command downloads and starts it:
ollama run llama3.1:70bOllama's default download is Q4_K_M (about 46.1 GB here). That is also the best quant that fits.
GPUs that run Llama 3.1 70B comfortably
Models that run well on the Apple M3 Max (64GB)
Run it in the cloud
Don't want to buy hardware? Run Llama 3.1 70B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.