What GPU do I need to run Qwen/Qwen3-235B-A22B?
235.1B parameters, published in BF16. View on Hugging Face
Set up Qwen3-235B-A22BQwen3-235B-A22B is published by Qwen on Hugging Face, with 343,103 downloads and 1,109 likes to date. It's a Qwen3MoeForCausalLM 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 Qwen3-235B-A22B at its published (BF16) precision: 6× RTX PRO 6000 on vastai, at $1.30/hr per GPU ($7.77/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3-235B-A22B: common questions
Can Qwen3-235B-A22B run on a single GPU?
No. At BF16 it needs 525.5 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 96.0 GB RTX PRO 6000, and it takes 6 of them.
How many GPUs do I need to run Qwen3-235B-A22B?
6 at BF16. It needs 525.5 GB of VRAM and the cheapest capable live offer is a 96.0 GB RTX PRO 6000 on vastai, so 6 of them come to $7.77/hr in total.
Does quantizing Qwen3-235B-A22B lower the GPU bill?
Yes. At BF16 the cheapest live fit is 6 RTX PRO 6000 cards on vastai at $7.77/hr. At INT4 (quantized) it drops to 3 RTX 8000 cards on akash at $0.661/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)
