How Much VRAM Does DeepSeek V3.2 Need to Run Locally?
See devices that run itDeepSeek V3.2 is a MoE model with 671B total parameters and 37B active per token. At Q4 it needs 376GB of VRAM to sit entirely on the GPU; with experts offloaded to system RAM it needs only 12GB of VRAM plus 365GB of RAM. The cheapest device that holds it is the Mac Studio M3 Ultra 512GB, with no used-price data yet, at roughly 19.4 tokens/s. In offload mode the cheapest card that runs it is the GeForce RTX 4080, at roughly 4 tokens/s.
DeepSeek V3.2 details
VRAM needed for DeepSeek V3.2 by quantization and context
Total at 8KMoE: all 671B parameters must stay resident in memory, while speed is set by the 37B active per token.
| Quantization | WeightsGB | Total at 8KGB | Total at 32KGB | Total at 128KGB |
|---|---|---|---|---|
| Q4_K_M | 374est. | 375.5 | 377.2 | 383.6 |
| Q5_K_M | 452.8est. | 454.3 | 455.9 | 462.3 |
| Q8_0 | 695.5est. | 697.1 | 698.7 | 705.1 |
| FP16 | 1,312.3est. | 1,313.9 | 1,315.5 | 1,321.9 |
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 160K limit show a dash.
Which GPUs can run DeepSeek V3.2?
Q4_K_M · 8K context · sorted by eBay used price| Device | VRAMGB | Used price | Est. t/s | Suggested context |
|---|---|---|---|---|
| Mac Studio M3 Ultra 512GB | 512 | —No listings | 19.4 | 128K |
Fits when weights + KV cache + runtime overhead is at or below usable memory, single card. "Offload" on MoE models means it runs with expert weights in system RAM (only attention layers and KV cache stay in VRAM); that speed assumes 70 GB/s RAM bandwidth. The context column is the largest tier that fits.
GPUs that run DeepSeek V3.2 with experts offloaded to RAM
Expert weights live in system RAM (needs at least 365 GB); VRAM holds only attention layers, shared experts and the KV cache, at least 12 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 V3.2 with Ollama, llama.cpp or vLLM
The Ollama library has no official tag for it yet.
vLLM serves the original-precision weights, which needs far more memory than GGUF and usually more than one GPU.
vllm serve deepseek-ai/DeepSeek-V3.2
File names follow that week's model-library snapshot; the definitions are in the methodology. Methodology
FAQ
How much VRAM does DeepSeek V3.2 need?
At Q4_K_M with an 8K context DeepSeek V3.2 needs about 376GB of VRAM; 452GB leaves comfortable headroom.
What is the cheapest GPU that runs DeepSeek V3.2?
The Mac Studio M3 Ultra 512GB: 512GB of VRAM at roughly 19.4 tokens/s. We have no used-price data for it yet.
Can you run DeepSeek V3.2 with Ollama?
Not yet: there is no official Ollama tag and no public GGUF build for it.