Text model · DeepSeek-V3
DeepSeek V3 requirements
DeepSeek-V3 family · 671B params (Mixture-of-Experts, 37B active) · released Mar 2025. Minimum to run at Q4_K_M: high-memory hardware.
Quantization sizes
| Quantization | Size on disk |
|---|---|
| Q2_K | 281 GB est |
| Q3_K_M | 328 GB est |
| Q4_K_M (default) | 376.66 GB |
| Q5_K_M | 478.1 GB est |
| Q6_K | 550.2 GB est |
| Q8_0 | 712.9 GB est |
| FP16 | 1342 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
ollama run deepseek-v3:671b llama-cli -hf unsloth/DeepSeek-V3-0324-GGUF:Q4_K_M lms get unsloth/DeepSeek-V3-0324-GGUF Which devices can run DeepSeek V3?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
AMD GPUs
FAQ
How much VRAM or RAM does DeepSeek V3 need?
At Q4_K_M, DeepSeek V3 needs about 383.7 GB (weights ~376.66 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~719.9 GB.
Can DeepSeek V3 run on a laptop?
DeepSeek V3 is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.
Is DeepSeek V3 cheaper to run because it is a MoE model?
It is faster, not lighter. DeepSeek V3 activates only 37B of 671B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 671B.
Can I use DeepSeek V3 commercially?
Yes. DeepSeek V3 is licensed MIT, which permits commercial use.
DeepSeek V3 (0324 build), 671B sparse MoE (37B active). Q4_K_M is ~377GB across a 9-file series. Low-bit dynamic quants fit ~150GB. Size from the unsloth GGUF repo.
Sources
Memory figures are estimates. See methodology.