# PerGB > PerGB ranks live eBay listings for graphics cards, memory, SSDs, CPUs and motherboards by price per GB (per GB of VRAM, memory or storage), per core or per point of speed, against the rest of the market for the same part. Prices come from eBay's API, are searched every six hours and shown only while under 6 hours old; performance, AI writing speeds and builds are estimates from published specs. ## Parts - [GPUs](https://pergb.com/gpus/): every graphics card, price against performance, price per GB of VRAM - [Memory](https://pergb.com/memory/): RAM by type, speed and stick size, priced per GB - [SSDs](https://pergb.com/ssd/): SSDs by type and capacity, priced per TB - [CPUs](https://pergb.com/cpu/): server, workstation and desktop CPUs with a speed score, gaming score, memory bandwidth and PCIe - [Motherboards](https://pergb.com/motherboards/): boards with the CPU generations each runs, slots and PCIe - [Accessories](https://pergb.com/accessories/): SXM adapters and GPU servers ## Tools - [What can I run?](https://pergb.com/run/): the cheapest GPUs that hold a local AI model - [Build a platform](https://pergb.com/build/): CPU, motherboard and memory priced together against speed and AI writing speed - [Best GPUs](https://pergb.com/best/): best GPUs for local AI by budget and VRAM - [Compare GPUs](https://pergb.com/compare/): GPUs side by side ## Guides - [How much VRAM do you need to run a 70B model?](https://pergb.com/guides/how-much-vram-for-a-70b-model/): What Llama 3.3 70B takes at each quantisation, and the cheapest GPUs that hold it today. - [Can you run big AI models on a CPU instead of GPUs?](https://pergb.com/guides/can-you-run-big-ai-models-on-a-cpu/): When server memory beats a stack of GPUs, and the cheapest platforms for the biggest models. - [Does the CPU matter for AI if you're using GPUs?](https://pergb.com/guides/does-cpu-matter-for-ai-with-a-gpu/): What the CPU does in a GPU rig for local LLMs: PCIe lanes, offloading to system RAM, AVX-512 and AMX, and which CPU to buy. - [Why do memory channels matter for AI, and how many does your CPU have?](https://pergb.com/guides/why-memory-channels-matter-for-ai/): Bandwidth by platform: desktop dual channel against 8 and 12 channel servers. - [DDR4 or DDR5 for running AI models?](https://pergb.com/guides/ddr4-vs-ddr5-for-ai/): What each channel gives, and what a GB of each costs on eBay today. - [Is a used RTX 3090 still worth it for AI?](https://pergb.com/guides/is-a-used-rtx-3090-worth-it-for-ai/): Its price per GB of VRAM against the other 24 GB+ cards on eBay right now. - [What's the cheapest way to run DeepSeek R1 or V3 (671B) at home?](https://pergb.com/guides/cheapest-way-to-run-deepseek-at-home/): About 400 GB at Q4: why a server with lots of memory beats GPUs, and the cheapest platforms now. - [Which CPU gives the most gaming performance per dollar?](https://pergb.com/guides/best-cpu-for-gaming-per-dollar/): Every desktop chip's gaming score against its lowest price today. - [Which motherboard for an AMD EPYC 7002 or 7003?](https://pergb.com/guides/which-motherboard-for-epyc-7002-7003/): What each SP3 board runs (it differs by model and revision), its PCIe and slots, and the price now. - [Does PCIe 3.0, 4.0 or 5.0 matter for GPUs and AI?](https://pergb.com/guides/does-pcie-version-matter-for-gpus/): When the PCIe generation and lane count matter, and what each platform gives. - [RDIMM, UDIMM or LRDIMM: which memory does your system take?](https://pergb.com/guides/rdimm-vs-udimm/): Registered and unbuffered memory, which platforms take which, and what each costs per GB now. - [How do you spot a scam or fake GPU listing on eBay?](https://pergb.com/guides/how-to-spot-a-scam-gpu-listing/): The warning signs, and how this site flags listings that look too good to be true. ## About - [About](https://pergb.com/about/): how prices are ranked and where they come from - [Privacy](https://pergb.com/privacy/)