Hardware
GeForce RTX 5090 32GB
Card only. 32 GB GDDR7 according to NVIDIA. Still too small for 70B Q4.
Memory
32 GB VRAMBandwidth
1792 GB/swww.nvidia.com/en-eu/geforce/graphics-cards/50-series/Price
$7,023€6,273
15 Oct 2026
PriceSquirrelCheapest tracked EU listing on that page on 15 Oct 2026: €6,273 at Compumsa (BE), MSI Gaming Trio OC. PriceSquirrel's buyer guide the same day marks that Compumsa line out of stock.
Which models fit
Estimate at 8,192 tokens, or the model's maximum when that is shorter. full means the formula fits in usable memory. offload means GPU plus system RAM. no means it does not fit. This is not a measured file.
| Model | Q4estimate | Q5estimate | Q8estimate | FP16estimate |
|---|---|---|---|---|
| Llama 3.2 3B | full | full | full | full |
| Llama 3.1 8B | full | full | full | full |
| Mistral 7B v0.3 | full | full | full | full |
| Gemma 2 9B | full | full | full | full |
| Qwen2.5 14B | full | full | full | no |
| Phi-4 14B | full | full | full | no |
| Gemma 2 27B | full | full | no | no |
| Qwen2.5 32B | full | full | no | no |
| Llama 3.3 70B | no | no | no | no |
| Qwen2.5 72B | no | no | no | no |
| DeepSeek-R1-Distill 70B | no | no | no | no |