What GPU do I need to run deepseek-ai/DeepSeek-V3-0324?
684.5B parameters, published in F8_E4M3. View on Hugging Face
Set up DeepSeek-V3-0324DeepSeek-V3-0324 is published by deepseek-ai on Hugging Face, with 1,090,042 downloads and 3,166 likes to date. It's a DeepseekV3ForCausalLM model built for text-generation, published natively in F8_E4M3.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run DeepSeek-V3-0324 at its published (F8_E4M3) precision: 8× RTX PRO 6000 on runpod, at $1.64/hr per GPU ($13.12/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
DeepSeek-V3-0324: common questions
Can DeepSeek-V3-0324 run on a single GPU?
No. At FP8 (native) it needs 765.0 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 96.0 GB RTX PRO 6000, and it takes 8 of them.
Is DeepSeek-V3-0324 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 765.0 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 382.5 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How many GPUs do I need to run DeepSeek-V3-0324?
8 at FP8 (native). It needs 765.0 GB of VRAM and the cheapest capable live offer is a 96.0 GB RTX PRO 6000 on runpod, so 8 of them come to $13.12/hr in total.
Does quantizing DeepSeek-V3-0324 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is 8 RTX PRO 6000 cards on runpod at $13.12/hr. At INT4 (quantized) it drops to 8 RTX 8000 cards on akash at $1.76/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More deepseek-ai models
- DeepSeek-OCR (3.3B, BF16)
- DeepSeek-R1 (684.5B, F8_E4M3)
- DeepSeek-V3.2 (685.4B, F8_E4M3)
- DeepSeek-V3 (684.5B, F8_E4M3)
- DeepSeek-OCR-2 (3.4B, BF16)
- DeepSeek-R1-0528-Qwen3-8B (8.2B, BF16)
