GPUs tracked41Price history3 dayssince Sep 3, 2026Price points (24h)11,753 pointsBiggest 24h dropBiggest 24h riseData updated Sep 5, 2026

How Much VRAM Does DeepSeek V4 Pro Need to Run Locally?

See devices that run it

DeepSeek V4 Pro is a MoE model with 1,600B total parameters and 49B active per token. At Q4 it needs 894GB of VRAM to sit entirely on the GPU; with experts offloaded to system RAM it needs only 17GB of VRAM plus 879GB of RAM. No single card in the database fits it; it needs multiple GPUs or the unified memory of a Mac Studio. In offload mode the cheapest card that runs it is the Radeon RX 7900 XT, at roughly 3 tokens/s.

DeepSeek V4 Pro details

Launch dateAug 13, 2026
Revision0813
LicenseMIT
ArchitectureMoE
Ollama tag
Min VRAM at Q4894 GB · Q4_K_M · 8K
Experts offloaded17 GB VRAM + 879 GB RAM
Parameters1,600B
MoE49B
Layers61
Hidden size7,168
KV heads1
Head dim512
Max context1M
VendorDeepSeek

VRAM needed for DeepSeek V4 Pro by quantization and context

Total at 8K

MoE: all 1,600B parameters must stay resident in memory, while speed is set by the 49B active per token.

QuantizationWeightsGBTotal at 8KGBTotal at 32KGBTotal at 128KGB
1-bit375.5est.377.5380.3391.8
2-bit594.6est.596.5599.4610.8
3-bit766.7est.768.6771.5782.9
4-bit849.7GGUF893.8896.6908.1
5-bit1,079.6est.1,081.51,084.41,095.8
8-bit873.4GGUF1,660.51,663.31,674.7
FP163,129.2est.3,131.23,134.13,145.5

Total = weights + KV cache (FP16) + 1GB runtime overhead. Weights marked GGUF are measured file sizes from the repository; the rest are estimated from bytes per parameter. Contexts beyond this model's 1M limit show a dash. Each tier takes whichever file of that bit width the repository has, preferring unsloth dynamic quants, so the exact file name varies by model.

Which GPUs can run DeepSeek V4 Pro?

Q4_K_M · 8K context · sorted by eBay used price

No single card in the database fits DeepSeek V4 Pro: it needs at least 894GB of VRAM at Q4_K_M with an 8K context.

A multi-GPU build needs at least 894GB of VRAM in total.

None of the unified-memory machines in the database fit it either.

GPUs that run DeepSeek V4 Pro with experts offloaded to RAM

Expert weights live in system RAM (needs at least 879 GB); VRAM holds only attention layers, shared experts and the KV cache, at least 17 GB at Q4. Speed is bound by RAM bandwidth (estimated at 70 GB/s) and is far slower than a full-VRAM setup.

Run DeepSeek V4 Pro with Ollama, llama.cpp or vLLM

Ollama

The Ollama library has no official tag for it yet.

llama.cpp

llama.cpp pulls the GGUF straight from Hugging Face; -c sets the context length.

llama-server -hf unsloth/DeepSeek-V4-Pro-0813-GGUF:Q4_K_M -c 8192
vLLM

vLLM serves the original-precision weights, which needs far more memory than GGUF and usually more than one GPU.

vllm serve deepseek-ai/DeepSeek-V4-Pro-0813

File names follow that week's model-library snapshot; the definitions are in the methodology. Methodology

FAQ

How much VRAM does DeepSeek V4 Pro need?

At Q4_K_M with an 8K context DeepSeek V4 Pro needs about 894GB of VRAM; 1,076GB leaves comfortable headroom.

What is the cheapest GPU that runs DeepSeek V4 Pro?

No single card in the database fits DeepSeek V4 Pro; it needs multiple GPUs or a Mac Studio's unified memory.

Can you run DeepSeek V4 Pro with Ollama?

Not yet: the Ollama library has no official tag for it. You can load the GGUF with llama.cpp instead.