Can the Apple M2 Pro (32GB) run Llama 3.1 70B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the Apple M2 Pro (32GB) has 21.4 GB usable. You could offload some layers to system RAM, but it will be very slow.
Run it on a rented GPU
On a cloud GPU with enough memory, the same command you'd use locally works:
ollama run llama3.1:70bAt Q4_K_M it needs about 46.1 GB, so pick a GPU with at least 48 GB.
Run it in the cloud
Too big for the Apple M2 Pro (32GB)? Run Llama 3.1 70B on a rented GPU instead.
Rent a cloud GPU by the hour. No upfront cost, stop any time.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 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 | Too big | — | |
| Q3_K_M | Noticeably degraded | 37.8 GB | Too big | — | |
| Q2_K | Heavily degraded | 29.8 GB | Too big | — |
GPUs that run Llama 3.1 70B comfortably
Frequently asked questions
Can Apple M2 Pro (32GB) run Llama 3.1 70B?
No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the Apple M2 Pro (32GB) has 21.4 GB usable. You could offload some layers to system RAM, but it will be very slow.
How much VRAM does Llama 3.1 70B need?
About 46.1 GB at Q4_K_M with 8,192 tokens of context, and about 144.5 GB at full FP16 precision.
How fast is Llama 3.1 70B on the Apple M2 Pro (32GB)?
It does not fit in the Apple M2 Pro (32GB)'s memory, so most layers would run from system RAM and generation would be very slow.