Qwen3 30B-A3B hardware requirements
30.5B parameters (3.3B active, mixture of experts). Needs about 19.9 GB at Q4_K_M with 8K context. Model card.
Memory needed at each quantization
| Quant | Quality | 8K context | 32K context |
|---|---|---|---|
| FP16 | Full quality | 62.4 GB | 64.8 GB |
| Q8_0 | Near-lossless | 33.8 GB | 36.2 GB |
| Q6_K | Excellent | 26.4 GB | 28.8 GB |
| Q5_K_M | Very good | 23.1 GB | 25.5 GB |
| Q4_K_M | Good, most popular | 19.9 GB | 22.3 GB |
| Q3_K_M | Noticeably degraded | 16.3 GB | 18.7 GB |
| Q2_K | Heavily degraded | 12.8 GB | 15.3 GB |
Run it with Ollama: ollama run qwen3:30b (downloads Q4_K_M by default).
Run it in the cloud
Don't want to buy hardware? Run Qwen3 30B-A3B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.
Every GPU and Mac checked
| GPU | Runs? | Best fit |
|---|---|---|
| NVIDIA RTX 3060 12GB | No | Needs ~19.9 GB at Q4_K_M; 12 GB available |
| NVIDIA RTX 3070 | No | Needs ~19.9 GB at Q4_K_M; 8 GB available |
| NVIDIA RTX 3080 10GB | No | Needs ~19.9 GB at Q4_K_M; 10 GB available |
| NVIDIA RTX 3090 | Yes | Q5_K_M · ~23.1 GB · ~239 tok/s |
| NVIDIA RTX 4060 | No | Needs ~19.9 GB at Q4_K_M; 8 GB available |
| NVIDIA RTX 4060 Ti 16GB | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~140 tok/s |
| NVIDIA RTX 5060 Ti 16GB | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~217 tok/s |
| NVIDIA RTX 4070 | No | Needs ~19.9 GB at Q4_K_M; 12 GB available |
| NVIDIA RTX 4070 Ti Super | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~326 tok/s |
| NVIDIA RTX 4080 | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~348 tok/s |
| NVIDIA RTX 4090 | Yes | Q5_K_M · ~23.1 GB · ~258 tok/s |
| NVIDIA RTX 5070 | No | Needs ~19.9 GB at Q4_K_M; 12 GB available |
| NVIDIA RTX 5070 Ti | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~434 tok/s |
| NVIDIA RTX 5080 | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~465 tok/s |
| NVIDIA RTX 5090 | Yes | Q6_K · ~26.4 GB · ~397 tok/s |
| AMD Radeon RX 7800 XT | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~303 tok/s |
| AMD Radeon RX 7900 XTX | Yes | Q5_K_M · ~23.1 GB · ~245 tok/s |
| Apple M4 (16GB) | No | Needs ~19.9 GB at Q4_K_M; 10.7 GB available |
| Apple M1 (16GB) | No | Needs ~19.9 GB at Q4_K_M; 10.7 GB available |
| Apple M2 Pro (32GB) | Yes | Q4_K_M · ~19.9 GB · ~60 tok/s |
| Apple M3 Max (64GB) | Yes | Q8_0 · ~33.8 GB · ~68 tok/s |
| Apple M4 Pro (48GB) | Yes | Q8_0 · ~33.8 GB · ~47 tok/s |
| Apple M4 Max (128GB) | Yes | FP16 · ~62.4 GB · ~50 tok/s |
| Apple M2 Ultra (192GB) | Yes | FP16 · ~62.4 GB · ~73 tok/s |