NVIDIA Tesla P40 24GB
Cheap 24GB, but Pascal has very slow FP16 (run FP32 or llama.cpp quantized). ~250W, passive, needs 8-pin EPS (CPU) power adapter. Fine for budget LLM inference, poor for training.
NVIDIA · gpu-server · 24 GB VRAM · 250 W · tags: server, pascal, passive, budget, cuda
EU / DE trend
No history points for this filter.
US trend
No history points for this filter.
Accepted offers (0)
No live price yet. We only show prices we could read from a shop page — no estimates.
Search used listings
Server GPUs are scam-prone. Check seller history and photos; anything under about €120 is likely broken, parts-only or fake.