| GPU |
VRAM |
Price (€) |
Bandwidth (TB/s) |
TFLOP16 |
€/GB |
€/TB/s |
€/TFLOP16 |
| NVIDIA H200 NVL |
141GB |
36284 |
4.89 |
1671 |
257 |
7423 |
21 |
| NVIDIA RTX PRO 6000 Blackwell |
96GB |
8450 |
1.79 |
126.0 |
88 |
4720 |
67 |
| NVIDIA RTX 5090 |
32GB |
2299 |
1.79 |
104.8 |
71 |
1284 |
22 |
| AMD RADEON 9070XT |
16GB |
665 |
0.6446 |
97.32 |
41 |
1031 |
7 |
| AMD RADEON 9070 |
16GB |
619 |
0.6446 |
72.25 |
38 |
960 |
8.5 |
| AMD RADEON 9060XT |
16GB |
382 |
0.3223 |
51.28 |
23 |
1186 |
7.45 |
This post is part "hear me out" and part asking for advice.
Looking at the table above AI gpus are a pure scam, and it would make much more sense to (atleast looking at this) to use gaming gpus instead, either trough a frankenstein of pcie switches or high bandwith network.
so my question is if somebody has build a similar setup and what their experience has been. And what the expected overhead performance hit is and if it can be made up for by having just way more raw peformance for the same price.
Yeah i should have specified for at home when saying its a scam, i honestly doubt the companies that are buying thousands of B200s for datacenters are even looking at their pricetags lmao.
Anyway the end goal is to run something like Qwen3-235B at fp8, with some very rough napkin math 300GB vram with the cheapest option the 9060XT comes down at €7126 with 18 cards, which is very affordable. But ofcourse that this is theoretically possible does not mean it will actually work in practice, which is what im curious about.
The inference engine im using vLLM supports ROCm so CUDA should not be strictly required.