Can I run Llama 3.1 70B on Apple M3 Pro (36GB)?
Not comfortably: Llama 3.1 70B only runs on Apple M3 Pro (36GB) with Q2_K by offloading part of the model to system RAM, which is much slower (often a few tokens/s). Smaller models or lower quantisations fit entirely in memory.
Memory by quantisation (8,192-token context)
| Quantisation | Memory | Verdict | Est. speed |
|---|---|---|---|
| F16Unquantized reference | 136.0 GiB | Does not fit | — |
| Q8_0Near-lossless | 74.4 GiB | Does not fit | — |
| Q6_KVery close to F16 | 58.5 GiB | Needs CPU offload | — |
| Q5_K_MGreat quality/size | 51.3 GiB | Needs CPU offload | — |
| Q4_K_MBest default for most | 44.4 GiB | Needs CPU offload | — |
| IQ4_XSSmaller 4-bit (imatrix) | 39.5 GiB | Needs CPU offload | — |
| Q3_K_MNoticeable loss | 36.7 GiB | Needs CPU offload | — |
| Q2_KLast resort; big loss | 32.1 GiB | Needs CPU offload | — |
Apple M3 Pro (36GB) offers about 36 GiB of memory (75% usable for a model) at 150 GB/s. Speed is a bandwidth-bound estimate of single-stream generation at 65% efficiency; real results vary by runtime, drivers and settings, so measure on your machine.
How this is calculated
Weights ≈ parameters × bits per weight ÷ 8. KV cache ≈ 2 × 80 layers × 8 KV heads × 128 head dim × 2 bytes per token. Decode speed ≈ efficiency × memory bandwidth ÷ bytes read per token. Learn the maths in VRAM math and memory bandwidth, or try the VRAM calculator.
Llama 3.1 70B on other hardware
Similar models on Apple M3 Pro (36GB)
Running slowly or out of memory? See CUDA out of memory and the quantisation lesson.