Models / Qwen3 30B A3B / Calculator

Qwen3 30B A3B cost & VRAM calculator

What does Qwen3 30B A3B cost to run for your workload, and can you run it on your own hardware? Set your workload below - we compute per-provider API cost live and tell you honestly whether local hardware can run it.

Your workload

Casual Power user Team of 5 Codebase task

Qwen3 30B A3B runs an always-on thinking mode. Reasoning (thinking) tokens are billed at the output rate ($15.00/M), so count them here to see the thinking portion of your bill.

API cost for your workload

Provider Rate ($/1M) Monthly cost
DeepInfra $0.12 in · $0.50 out $0.0 cheapest
Alibaba $0.13 in · $0.52 out $0.0 cheapest

Monthly cost is an estimate from list prices and your workload - verify against the provider before committing. Cached fraction applies the cache rate to that share of input.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Qwen3 30B A3B fits on individual rigs. Here's the hardware that runs it comfortably; the full per-quant VRAM matrix and tok/s estimates live on the model page.

4x H100 80GB (320GB) 320GB Q4_K_M
1951.5t/s
NVIDIA DGX Station 748GB 748GB Q4_K_M
1165.1t/s
8x RTX 3090 rack (192GB) 192GB Q4_K_M
1090.7t/s
4x RTX 5090 (128GB) 128GB Q4_K_M
1043.9t/s
AMD Instinct MI300X (192GB) 192GB Q4_K_M
775.5t/s
4x RTX 4090 (96GB) 96GB Q4_K_M
587.2t/s
2x RTX 5090 (64GB) 64GB Q4_K_M
522.0t/s
2x RTX 3090 (48GB) 48GB Q4_K_M
272.7t/s
Single RTX 5090 (32GB) 32GB Q4_K_M
261.0t/s
RTX PRO 6000 Blackwell (96GB) 96GB Q4_K_M
261.0t/s
Mac Studio M4 Ultra 192GB 192GB Q4_K_M
173.5t/s
Mac Studio M4 Ultra 512GB 512GB Q4_K_M
173.5t/s
Single RTX 4090 (24GB) 24GB Q4_K_M
146.8t/s
MacBook Pro M5 Max 128GB 128GB Q4_K_M
97.6t/s
Dual EPYC 9004 + 768GB DDR5-4800 768GB Q4_K_M
67.1t/s
DGX Spark 128GB unified 128GB Q4_K_M
39.8t/s
Ryzen AI Max+ 395 128GB 128GB Q4_K_M
37.3t/s
Jetson AGX Orin 64GB 64GB Q4_K_M
29.8t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q4_K_M
29.8t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q4_K_M
22.4t/s
Q4_K_M
15.5GB weights 15.5GB min 17.4GB rec
Q8_0
31.0GB weights 31.0GB min 35.0GB rec

Want the own-vs-rent payback (capex vs your monthly API bill)? The budget tool computes that against representative rigs.

Full model card API pricing table Generic token calculator