Apple M1 Max (32-core GPU, 64GB) × Qwen3 235B-A22B (MoE)
Can the Apple M1 Max (32-core GPU, 64GB) run Qwen3 235B-A22B (MoE)?
No
No. Qwen3 235B-A22B (MoE) needs at least ~120 GB, but the Apple M1 Max (32-core GPU, 64GB) has ~48.0 GB usable. You would need CPU offloading (much slower) or more memory.
By quantization (8K context)
| Quant | Memory needed | Fits? | Est. tok/s |
|---|---|---|---|
| Q3_K_M | 120 GB | ❌ | — |
| 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 M2 Ultra (76-core GPU, 192GB) — ~18.4 tok/s at Q3_K_M
- Apple M3 Ultra (80-core GPU, 512GB) — ~14.6 tok/s at Q4_K_M
Rent a GPU instead
Qwen3 235B-A22B (MoE) doesn't fit here? Rent a cloud GPU with enough VRAM by the hour and run it there.
Vast.ai — cheap marketplace GPUs · RunPod — on-demand GPU pods
Affiliate links: we may earn a commission at no extra cost to you.
Get new models & benchmarks in your inbox
No spam. Unsubscribe anytime by replying to any email.