Can the RTX 3090 run Qwen3 32B?
Just. Qwen3 32B at Q4_K_M needs about 20.8 GB of the RTX 3090's 24 GB, running at an estimated 29 tok/s. Keep context short and close other GPU apps.
Every quantization
Qwen3 32B (32B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 19 GB | 20.8 GB | Tight | ~29 tok/s |
| Q5_K_M | 23 GB | 24.8 GB | Too big | - |
| Q8_0 | 34 GB | 35.8 GB | Too big | - |
| FP16 | 64 GB | 65.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 3090's 936 GB/s bandwidth (XiongjieDai/GPU-Benchmarks-on-LLM-Inference). Long contexts need more memory and run slower.
Run it
Copy, paste, go
ollama run qwen3:32bllama-server -hf Qwen/Qwen3-32B-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Qwen3 32B details →
Compare
Same model, other hardware - and other models on this card
Qwen3 32B on other hardware
- RTX 5090~54 tok/s
- RTX 5090 D~54 tok/s
- RTX 6000D~47 tok/s
- RTX 4090~33 tok/s
- Radeon RX 7900 XTX~29 tok/s
- MacBook Pro 16" M4 Max~16 tok/s
- Arc Pro B60~14 tok/s
- DGX Spark (GB10)~8.3 tok/s
Also runs on the RTX 3090
- GLM-4.7-Flash~211 tok/s
- Qwen3-30B-A3B-Instruct-2507~206 tok/s
- Qwen3.6 27B~34 tok/s
- Qwen3.8 27B~34 tok/s
- Gemma 4 26B A4B~161 tok/s
- gpt-oss-20b~182 tok/s
- Qwen2.5-Coder-14B-Instruct~61 tok/s
- Qwen3 14B~68 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 3090 run Qwen3 32B?
Just. Qwen3 32B at Q4_K_M needs about 20.8 GB of the RTX 3090's 24 GB, running at an estimated 29 tok/s. Keep context short and close other GPU apps.
How much VRAM does Qwen3 32B need?
About 19 GB of weights at Q4_K_M, 34 GB at Q8_0 and 64 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen3 32B on the RTX 3090?
Roughly 29 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 3090's 936 GB/s memory bandwidth.