Can the NVIDIA RTX 5090 run Qwen2.5 32B?
Yes
QuantQ6_KExcellent
Memory29.6 GBof 32 GB
Speed~40tokens/s
Yes. The NVIDIA RTX 5090 can run Qwen2.5 32B fully in VRAM at Q6_K (excellent), using about 29.6 GB of the 32 GB available, at roughly 40 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 68.3 GB | Too big | — |
| Q8_0 | Near-lossless | 37.6 GB | Too big | — |
| Q6_K | Excellent | 29.6 GB | Fits | ~40 tok/s |
| Q5_K_M | Very good | 26.1 GB | Fits | ~46 tok/s |
| Q4_K_M | Good, most popular | 22.6 GB | Fits | ~54 tok/s |
| Q3_K_M | Noticeably degraded | 18.8 GB | Fits | ~67 tok/s |
| Q2_K | Heavily degraded | 15 GB | Fits | ~87 tok/s |
How to run Qwen2.5 32B on the NVIDIA RTX 5090
With Ollama installed, one command downloads and starts it:
ollama run qwen2.5:32bOllama's default download is Q4_K_M (about 22.6 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.
GPUs that run Qwen2.5 32B comfortably
- NVIDIA RTX 3090 (24 GB)
- AMD Radeon RX 7900 XTX (24 GB)
- NVIDIA RTX 4090 (24 GB)
- Apple M4 Pro (48GB)
- Apple M3 Max (64GB)
Models that run well on the NVIDIA RTX 5090
Run it in the cloud
Don't want to buy hardware? Run Qwen2.5 32B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.