What GPU do I need to run Qwen/Qwen-72B?
72.3B parameters, published in BF16. View on Hugging Face
Set up Qwen-72BQwen-72B is published by Qwen on Hugging Face, with 3,244,398 downloads and 361 likes to date. It's a QWenLMHeadModel model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen-72B at its published (BF16) precision: 7× RTX 3090 on akash, at $0.147/hr per GPU ($1.03/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen-72B: common questions
Can Qwen-72B run on a single GPU?
No. At BF16 it needs 161.6 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 24.0 GB RTX 3090, and it takes 7 of them.
How many GPUs do I need to run Qwen-72B?
7 at BF16. It needs 161.6 GB of VRAM and the cheapest capable live offer is a 24.0 GB RTX 3090 on akash, so 7 of them come to $1.03/hr in total.
Does quantizing Qwen-72B lower the GPU bill?
Yes. At BF16 the cheapest live fit is 7 RTX 3090 cards on akash at $1.03/hr. At INT4 (quantized) it drops to one RTX 8000 on akash at $0.221/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen models
- Qwen3-0.6B (752M, BF16)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
- Qwen2.5-7B-Instruct (7.6B, BF16)
- Qwen3-VL-8B-Instruct (8.8B, BF16)
