Apple M2 Ultra (76-core GPU, 192GB) × Qwen3 235B-A22B (MoE)
Can the Apple M2 Ultra (76-core GPU, 192GB) run Qwen3 235B-A22B (MoE)?
Yes, usable
Yes. The Apple M2 Ultra (76-core GPU, 192GB) can run Qwen3 235B-A22B (MoE) at up to Q3_K_M (needs ~120 GB of 144 GB usable), at an estimated ~18.4 tokens/sec at Q3_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 | 120 GB | ✅ | ~18.4 |
| Q4_K_M | 149 GB | ❌ | — |
| Q5_K_M | 175 GB | ❌ | — |
| Q6_K | 202 GB | ❌ | — |
| Q8_0 | 260 GB | ❌ | — |
| F16 | 486 GB | ❌ | — |
Fastest hardware for Qwen3 235B-A22B (MoE)
- Apple M3 Ultra (80-core GPU, 512GB) — ~14.6 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.