aliteq.

The best GPU for running DeepSeek V4 Pro (MoE) (2026)

Ranked from live rental prices and computed VRAM fit, not opinion. Every card is judged at FP4 + FP8, the format DeepSeek V4 Pro (MoE)ships in (its 4-bit builds are no smaller, so it's also what people run) — at 8k context, so it's a fair comparison. A card that can't fit DeepSeek V4 Pro (MoE)at that quality isn't listed, because it could only run a crushed version.

No single card in our database fits DeepSeek V4 Pro (MoE) at its own FP4 + FP8 release and 8k context — at 1599B parameters it needs more memory than any one consumer or workstation GPU has, so this is a multi-GPU or datacenter decision.

See one fast card vs two big ones and the cheapest way to serve a 70B, or the full breakdown on the cost-to-run page.

Check it yourself

See exactly what fits, at any context length

Running DeepSeek V4 Pro (MoE): common questions

How much VRAM do you need to run DeepSeek V4 Pro (MoE)?
In its own FP4 + FP8 release and at 8k context, DeepSeek V4 Pro (MoE) needs about 806.2 GB — 805.3 GB of weights plus 0.0 GB of KV cache and ~0.8 GB overhead. So you want a card with at least that much free memory; the KV cache grows if you use longer context.
Can an RTX 4090 run DeepSeek V4 Pro (MoE)?
Not in its own FP4 + FP8 release — DeepSeek V4 Pro (MoE) needs more than the card's 24 GB at that quality and 8k context. Its FP4 + FP8 release is already the small build (its 4-bit GGUFs are about the same size), so you'd need a bigger card, two cards, or to spill part of it into system RAM, which is much slower.
Can an RTX 3090 run DeepSeek V4 Pro (MoE)?
Not in its own FP4 + FP8 release — DeepSeek V4 Pro (MoE) needs more than the card's 24 GB at that quality and 8k context. Its FP4 + FP8 release is already the small build (its 4-bit GGUFs are about the same size), so you'd need a bigger card, two cards, or to spill part of it into system RAM, which is much slower.
Can an RTX 4060 Ti 16GB run DeepSeek V4 Pro (MoE)?
Not in its own FP4 + FP8 release — DeepSeek V4 Pro (MoE) needs more than the card's 16 GB at that quality and 8k context. Its FP4 + FP8 release is already the small build (its 4-bit GGUFs are about the same size), so you'd need a bigger card, two cards, or to spill part of it into system RAM, which is much slower.

Before you buy

Best GPU for other models