PerGB

Cheapest GPUs to run DeepSeek V4.1 Flash 763B locally

DeepSeek V4.1 Flash 763B needs about 463 GB of VRAM at Q4 with an 8K-token context (811 GB at Q8). A mixture of experts: 8B to 16B active, with a very small attention cache. The cheapest way to hold it right now: 4 × H200 NVL for $219,319, about 148–223 tokens/s.

The cheapest setups right now

Live on eBay
SetupVRAMSpeed (est.)Price nowPowerSoftware
4 × H200 NVL564 GB96.8 GB spare148–223 tokens/s$219,319the 4 cheapest listings2,400 Wover a 15 A circuitCUDA 11.8 and newer

A set of cards is priced at that many of the cheapest live listings, shipping included. Speed: an estimate from memory bandwidth for one user chatting, within a third either way.

How it works

The memory a model needs is its weights at the quantisation you pick, plus the attention cache for the context and a little for working buffers. Q4 is what most people run at home, close to full quality at a third of the size. Each card keeps about 1 GB for itself, so two 24 GB cards hold 46 GB.

Writing each token reads every active weight once, so the speed is about the memory bandwidth divided by the model's size, times what the software gets out of the card (less off CUDA). Cards sharing a model layer by layer take turns, so a set runs about as fast as one card would. Treat it as a rough figure for one person chatting; a long prompt takes longer to read in.

Power is the cards' rated power. Over about 1,440 W with the rest of the PC, a set needs more than one 15 A circuit (or a 240 V one), and older cards often need a power cable adapter, which each card's page mentions.