Can I Run Qwen 3.7 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Written by Jakub Rusinowski · Last updated June 26, 2026
Yes, but it is tight
Yes, but it is tight — Qwen 3.7 35B-A3B at Q6_K needs about 31.4 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~0.6 GB before the runtime starts swapping. Expect ~209.4 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~209.4 tok/s
RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Qwen 3.7 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|
| F16 | 72.7 GB | ✗ No | — | — | 70 GB |
| Q8_0 | 39.9 GB | ✗ No | — | — | 37.2 GB |
| Q6_K | 31.4 GB | ✓ Yes | 8K | ~209.4 tok/s | 28.7 GB |
| Q5_K_M | 27.5 GB | ✓ Yes | 16K | ~220.9 tok/s | 24.8 GB |
| Q4_K_M | 23.8 GB | ✓ Yes | 32K | ~233 tok/s | 21.1 GB |
| Q3_K_M | 17.6 GB | ✓ Yes | 64K | ~256.6 tok/s | 14.9 GB |
| Q2_K | 14.2 GB | ✓ Yes | 64K | ~271.8 tok/s | 11.5 GB |
What to watch out for
- Only ~0.6 GB of headroom at Q6_K: a longer context or a second application can push this into swapping.
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
RTX 5090 desktop limitations
- 575 W board power — budget for a 1000 W+ PSU and the heat it puts into the room.
- Models larger than 32 GB must offload to system RAM, which costs roughly an order of magnitude in speed.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 32 GB of VRAM on the NVIDIA GeForce RTX 5090 at 1792 GB/s.
- 64 GB of system RAM available for CPU offload when a model exceeds VRAM.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run Qwen 3.7 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Yes, but it is tight — Qwen 3.7 35B-A3B at Q6_K needs about 31.4 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~0.6 GB before the runtime starts swapping. Expect ~209.4 tok/s (estimated), with room for about 8,192 tokens of context.
Which quantization of Qwen 3.7 should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 31.4 GB of the 32 GB available, downloads as roughly 28.7 GB, and runs at an estimated 209.4 tokens/sec with up to 8K of context.
What limits Qwen 3.7 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
Qwen 3.7 on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Qwen 3.7 model page | Check your hardware