Apple M3 Max (40-core GPU, 64GB) × Llama 3.3 70B Instruct
Can the Apple M3 Max (40-core GPU, 64GB) run Llama 3.3 70B Instruct?
Barely
Yes. The Apple M3 Max (40-core GPU, 64GB) can run Llama 3.3 70B Instruct at up to Q4_K_M (needs ~47.6 GB of 48.0 GB usable), at an estimated ~5.9 tokens/sec at Q4_K_M.
Speed is estimated from memory bandwidth calibrated with a measured 66.31 tok/s Llama 2 7B Q4_0 result (source). No direct public benchmark of this exact pair is recorded yet.
By quantization (8K context)
| Quant | Memory needed | Fits? | Est. tok/s |
|---|---|---|---|
| Q3_K_M | 38.9 GB | ✅ | ~7.4 |
| Q4_K_M | 47.6 GB | ✅ | ~5.9 |
| Q5_K_M | 55.3 GB | ❌ | — |
| Q6_K | 63.5 GB | ❌ | — |
| Q8_0 | 80.7 GB | ❌ | — |
| F16 | 149 GB | ❌ | — |
Fastest hardware for Llama 3.3 70B Instruct
- Apple M5 Max (40-core GPU, 128GB) — ~10.7 tok/s at Q4_K_M
- Apple M2 Ultra (76-core GPU, 192GB) — ~8.4 tok/s at Q4_K_M
- Apple M3 Ultra (80-core GPU, 512GB) — ~8.2 tok/s at Q4_K_M
- Apple M4 Max (40-core GPU, 128GB) — ~7.4 tok/s at Q4_K_M
- Apple M5 Pro (20-core GPU, 64GB) — ~5.9 tok/s at Q4_K_M
No suitable GPU? Rent one by the hour on Vast.ai or RunPod (affiliate links).
Get new models & benchmarks in your inbox
No spam. Unsubscribe anytime by replying to any email.