Apple M5 Max (40-core GPU, 128GB) × Gemma 3 27B
Can the Apple M5 Max (40-core GPU, 128GB) run Gemma 3 27B?
Yes
Yes. The Apple M5 Max (40-core GPU, 128GB) can run Gemma 3 27B at up to F16 (needs ~61.4 GB of 96.0 GB usable), at an estimated ~27.6 tokens/sec at Q4_K_M.
Speed is estimated from memory bandwidth calibrated with a measured 119.92 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 | 18.7 GB | ✅ | ~34.3 |
| Q4_K_M | 22.1 GB | ✅ | ~27.6 |
| Q5_K_M | 25.1 GB | ✅ | ~23.5 |
| Q6_K | 28.2 GB | ✅ | ~20.3 |
| Q8_0 | 34.9 GB | ✅ | ~15.7 |
| F16 | 61.4 GB | ✅ | ~8.4 |
Fastest hardware for Gemma 3 27B
- NVIDIA GeForce RTX 5090 — ~66.7 tok/s at Q4_K_M
- NVIDIA GeForce RTX 4090 — ~42.8 tok/s at Q4_K_M
- AMD Radeon RX 7900 XTX — ~42.4 tok/s at Q4_K_M
- NVIDIA GeForce RTX 3090 Ti — ~39.4 tok/s at Q4_K_M
- NVIDIA GeForce RTX 3090 — ~36.4 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.