Apple M2 Ultra (76-core GPU, 192GB) × Qwen3 30B-A3B (MoE)
Can the Apple M2 Ultra (76-core GPU, 192GB) run Qwen3 30B-A3B (MoE)?
Yes
Yes. The Apple M2 Ultra (76-core GPU, 192GB) can run Qwen3 30B-A3B (MoE) at up to F16 (needs ~64.4 GB of 144 GB usable), at an estimated ~88.5 tokens/sec at Q4_K_M.
Speed is estimated from memory bandwidth calibrated with a measured 94.27 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 | 16.9 GB | ✅ | ~106 |
| Q4_K_M | 20.7 GB | ✅ | ~88.5 |
| Q5_K_M | 24.0 GB | ✅ | ~77.1 |
| Q6_K | 27.5 GB | ✅ | ~67.9 |
| Q8_0 | 35.0 GB | ✅ | ~54.3 |
| F16 | 64.4 GB | ✅ | ~30.3 |
Fastest hardware for Qwen3 30B-A3B (MoE)
- NVIDIA GeForce RTX 5090 — ~272 tok/s at Q4_K_M
- NVIDIA GeForce RTX 4090 — ~175 tok/s at Q4_K_M
- AMD Radeon RX 7900 XTX — ~173 tok/s at Q4_K_M
- NVIDIA GeForce RTX 3090 Ti — ~161 tok/s at Q4_K_M
- NVIDIA GeForce RTX 3090 — ~148 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.