DeepSeek V3 — local AI model by DeepSeek
Written by Jakub Rusinowski · Last updated
DeepSeek's groundbreaking non-reasoning frontier model. Trained for just $5.5M — 1/10th the cost of comparable proprietary models. Uses a 685B MoE architecture (37B active parameters per token), topping the open-source leaderboard for coding, math, and general instruction following at launch. Previous generation — superseded by DeepSeek V4, which expands context to 1M tokens and improves MoE efficiency. Still widely used and supported.
Variants
The smallest DeepSeek V3 variant needs about 414 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| DeepSeek V3 (685B MoE) → 685B (37B active) | ~414.4 GB | 128,000 | ollama run deepseek-v3 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run DeepSeek V3 locally
Install Ollama, then pull the tag.
ollama run deepseek-v3Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: DeepSeek V3 (685B MoE)Can I run DeepSeek V3 on my GPU?
DeepSeek V3 — frequently asked questions
How much VRAM does DeepSeek V3 need?
DeepSeek V3 needs about 414 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek V3 (685B MoE) (414 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run DeepSeek V3 on an RTX 4090 (24 GB)?
DeepSeek V3's smallest variant needs about 414 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for DeepSeek V3?
Q4_K_M is the best balance of quality and VRAM for DeepSeek V3 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run DeepSeek V3 with Ollama?
Install Ollama, then run: ollama run deepseek-v3. This downloads DeepSeek V3 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.