Can the Apple M4 Pro (48GB) run Llama 3.1 70B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Only just. Llama 3.1 70B fits on the Apple M4 Pro (48GB) at Q2_K, which costs noticeable quality. Expect about 6 tokens/second. A card with more memory is a better experience.
Run it with Ollama
Ollama's default llama3.1:70b download is Q4_K_M, which needs about 46.1 GB, more than the 36 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.
New to this? Step-by-step setup for the Apple M4 Pro (48GB)
Run it in the cloud
Want full quality? Run Llama 3.1 70B on a bigger rented GPU.
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 36 GB the Apple M4 Pro (48GB) can use. macOS lets the GPU use about 36 GB of the 48 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 | Fits | ~6 tok/s |
GPUs that run Llama 3.1 70B comfortably
Models that run well on the Apple M4 Pro (48GB)
Frequently asked questions
Can Apple M4 Pro (48GB) run Llama 3.1 70B?
Only just. Llama 3.1 70B fits on the Apple M4 Pro (48GB) at Q2_K, which costs noticeable quality. Expect about 6 tokens/second. A card with more memory is a better experience.
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 M4 Pro (48GB)?
Roughly 6 tokens per second at Q2_K, estimated from the Apple M4 Pro (48GB)'s 273 GB/s memory bandwidth.