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

What Do You Need to Run DeepSeek Locally? VRAM by Version

DeepSeek currently has 5 versions you can deploy locally. The smallest, DeepSeek R1 Qwen3 8B, needs 7GB of VRAM at Q4; the largest, DeepSeek V3.2, needs 12GB. The cheapest device that gets one running is the GeForce RTX 2080 Ti, with no used-price data yet.

VRAM needed for each DeepSeek version

5 versions
VersionReleasedContext
DeepSeek R1 Qwen3 8BDense8.2BMay 29, 2025128K7GeForce RTX 2080 Ti · 11 GB1,003,991
DeepSeek R1 Distill Qwen 14BDense14.8BJan 20, 2025128K11GeForce RTX 2080 Ti · 11 GB396,404
DeepSeek R1 Distill Qwen 32BDense32.8BJan 20, 2025128K22Arc Pro B60 · 24 GB562,818
DeepSeek V4 FlashMoE284B (13B active)Jul 31, 20261M7plus 155 GB of RAMMac Studio M3 Ultra 512GB · 512 GB4,559,659
DeepSeek V3.2MoE671B (37B active)Dec 1, 2025160K12plus 365 GB of RAMMac Studio M3 Ultra 512GB · 512 GB1,559,697

Minimum VRAM = Q4_K_M weights + KV cache for an 8K context + 1GB runtime overhead, rounded up. The cheapest device is the first one that fits when sorting by median used price on the current price basis.

About DeepSeek

DeepSeek is published by DeepSeek under MIT. This page covers 5 versions ranging from 8.2B to 671B parameters; structure parameters and quantized sizes are synced weekly from Hugging Face.

VendorDeepSeek
LicenseMIT
Hugging Face orgdeepseek-ai