Can the NVIDIA RTX 3090 run Qwen3 235B-A22B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, Qwen3 235B-A22B needs about 144.7 GB, but the NVIDIA RTX 3090 has 24 GB usable. You could offload some layers to system RAM, but it will be very slow.
Run it on a rented GPU
On a cloud GPU with enough memory, the same command you'd use locally works:
ollama run qwen3:235bAt Q4_K_M it needs about 144.7 GB, so pick a GPU with at least 152 GB.
New to this? Step-by-step setup for the RTX 3090
Run it in the cloud
Too big for the NVIDIA RTX 3090? Run Qwen3 235B-A22B on a rented GPU instead.
Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 24 GB the NVIDIA RTX 3090 can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 472.4 GB | Too big | — | |
| Q8_0 | Near-lossless | 252 GB | Too big | — | |
| Q6_K | Excellent | 195 GB | Too big | — | |
| Q5_K_M | Very good | 169.4 GB | Too big | — | |
| Q4_K_M | Good, most popular | 144.7 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 117.1 GB | Too big | — | |
| Q2_K | Heavily degraded | 90.3 GB | Too big | — |
Measured speed from real RTX 3090 owners
Tokens per second that people measured on their own NVIDIA RTX 3090, next to our estimate.
No one has measured Qwen3 235B-A22B on the NVIDIA RTX 3090 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.
Have an RTX 3090? Add your real speed
One command times Qwen3 235B-A22B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.
macOS and Linux
curl -fsSL https://gpufit.dev/bench.sh | sh -s -- qwen3:235bWindows (PowerShell)
$env:GPUFIT_MODEL="qwen3:235b"; irm https://gpufit.dev/bench.ps1 | iexGPUs that run Qwen3 235B-A22B comfortably
Frequently asked questions
Can NVIDIA RTX 3090 run Qwen3 235B-A22B?
No. Even at Q4_K_M, Qwen3 235B-A22B needs about 144.7 GB, but the NVIDIA RTX 3090 has 24 GB usable. You could offload some layers to system RAM, but it will be very slow.
How much VRAM does Qwen3 235B-A22B need?
About 144.7 GB at Q4_K_M with 8,192 tokens of context, and about 472.4 GB at full FP16 precision.
How fast is Qwen3 235B-A22B on the NVIDIA RTX 3090?
It does not fit in the NVIDIA RTX 3090's memory, so most layers would run from system RAM and generation would be very slow.