Qwen on Apple M3
Can I run Qwen3 30B-A3B on an Mac Studio M3 Ultra 256GB?
Yes. Qwen3 30B-A3B at Q4_K_M uses 18.5 GB of the 192.0 GB available on a Mac Studio M3 Ultra 256GB, and runs at about 104 tokens per second. You can push the context to 128K.
Runs comfortably
18.5 GB of 192.0 GB · 10%0192 GB
Weights
17.3 GB
KV cache
0.8 GB
Runtime overhead
0.5 GB
Qwen3 30B-A3B at Q4_K_M leaves 173.5 GB spare on a Mac Studio M3 Ultra 256GB. There is room to raise the context length or move up a quantisation level.
Generation104tok/s
Prompt processing3584tok/s
Max context128Ktokens
KV per 1K tokens0GB
Every quantisation of Qwen3 30B-A3B on a Mac Studio M3 Ultra 256GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 56.9 GB | 58.1 GB | Runs comfortably | 128K | 49.3 |
| INT8 / W8A8 | 8.50 | 30.1 GB | 31.3 GB | Runs comfortably | 128K | 76.4 |
| Q8_0 (GGUF) | 8.50 | 30.1 GB | 31.3 GB | Runs comfortably | 128K | 76.4 |
| FP8 (E4M3) | 8.00 | 28.4 GB | 29.7 GB | Runs comfortably | 128K | 79.1 |
| Q6_K | 6.56 | 23.3 GB | 24.6 GB | Runs comfortably | 128K | 88.7 |
| Q5_K_M | 5.67 | 20.2 GB | 21.4 GB | Runs comfortably | 128K | 96.0 |
| Q5_K_S | 5.52 | 19.6 GB | 20.9 GB | Runs comfortably | 128K | 97.3 |
| Q4_K_M | 4.85 | 17.3 GB | 18.5 GB | Runs comfortably | 128K | 104 |
| Q4_K_S | 4.58 | 16.3 GB | 17.6 GB | Runs comfortably | 128K | 106 |
| Q4_0 | 4.55 | 16.2 GB | 17.5 GB | Runs comfortably | 128K | 107 |
| AWQ 4-bit | 4.25 | 16.0 GB | 17.2 GB | Runs comfortably | 128K | 108 |
| GPTQ 4-bit | 4.25 | 16.0 GB | 17.2 GB | Runs comfortably | 128K | 108 |
| MXFP4 | 4.25 | 16.0 GB | 17.2 GB | Runs comfortably | 128K | 108 |
| IQ4_XS | 4.25 | 15.2 GB | 16.4 GB | Runs comfortably | 128K | 110 |
| Q3_K_M | 3.91 | 14.0 GB | 15.2 GB | Runs comfortably | 128K | 114 |
| IQ3_M | 3.70 | 13.3 GB | 14.5 GB | Runs comfortably | 128K | 117 |
| IQ3_XXS | 3.06 | 11.1 GB | 12.3 GB | Runs comfortably | 128K | 125 |
| Q2_K | 2.63 | 9.6 GB | 10.8 GB | Runs comfortably | 128K | 132 |
| IQ2_XXS | 2.06 | 7.6 GB | 8.8 GB | Runs comfortably | 128K | 142 |
| IQ1_M | 1.75 | 6.5 GB | 7.7 GB | Runs comfortably | 128K | 148 |