Autor: Jakub Rusinowski · Ostatnia aktualizacja: 26 czerwca 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
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| 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 |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
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.
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.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving