Can the Apple M4 (16GB) run Qwen2.5 72B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, Qwen2.5 72B needs about 47.4 GB, but the Apple M4 (16GB) has 10.7 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 qwen2.5:72bAt Q4_K_M it needs about 47.4 GB, so pick a GPU with at least 48 GB.
New to this? Step-by-step setup for the Apple M4 (16GB)
Run it in the cloud
Too big for the Apple M4 (16GB)? Run Qwen2.5 72B on a rented GPU instead.
Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 10.7 GB the Apple M4 (16GB) can use. macOS lets the GPU use about 10.7 GB of the 16 GB unified memory by default.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 148.7 GB | Too big | — | |
| Q8_0 | Near-lossless | 80.5 GB | Too big | — | |
| Q6_K | Excellent | 62.9 GB | Too big | — | |
| Q5_K_M | Very good | 55 GB | Too big | — | |
| Q4_K_M | Good, most popular | 47.4 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 38.8 GB | Too big | — | |
| Q2_K | Heavily degraded | 30.5 GB | Too big | — |
GPUs that run Qwen2.5 72B comfortably
Models that run well on the Apple M4 (16GB)
Frequently asked questions
Can Apple M4 (16GB) run Qwen2.5 72B?
No. Even at Q4_K_M, Qwen2.5 72B needs about 47.4 GB, but the Apple M4 (16GB) has 10.7 GB usable. You could offload some layers to system RAM, but it will be very slow.
How much VRAM does Qwen2.5 72B need?
About 47.4 GB at Q4_K_M with 8,192 tokens of context, and about 148.7 GB at full FP16 precision.
How fast is Qwen2.5 72B on the Apple M4 (16GB)?
It does not fit in the Apple M4 (16GB)'s memory, so most layers would run from system RAM and generation would be very slow.