DeepSeek V4 Pro (Withdrawn Listings) — local AI model by DeepSeek
Written by Jakub Rusinowski · Last updated
Rank #1 open-weight model on every major benchmark. DeepSeek V4 Pro uses a massive 1.6 trillion parameter Mixture-of-Experts architecture with only 49 billion parameters active per token — giving frontier-tier intelligence at a fraction of the compute cost. Dominates coding, math, reasoning, and multilingual tasks.
Variants
The smallest DeepSeek V4 Pro (Withdrawn Listings) variant needs about 967 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.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 V4 Pro (Q4_K_M) 1.6T / 49B active | ~966.8 GB | 128,000 | ollama run deepseek-v4-pro:latest | |
| DeepSeek V4 Pro (API) API | ~966.8 GB | 128,000 | ollama run deepseek-v4-pro |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run DeepSeek V4 Pro (Withdrawn Listings) locally
Install Ollama, then pull the tag.
ollama run deepseek-v4-pro:latestPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Applies to: DeepSeek V4 Pro (Q4_K_M)No downloadable weights. Available through the vendor’s API only.
Applies to: DeepSeek V4 Pro (API)DeepSeek V4 Pro (Withdrawn Listings) — frequently asked questions
How much VRAM does DeepSeek V4 Pro (Withdrawn Listings) need?
DeepSeek V4 Pro (Withdrawn Listings) needs about 967 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek V4 Pro (Q4_K_M) (967 GB, Q4_K_M); DeepSeek V4 Pro (API) (967 GB, None (cloud)). On Apple Silicon, unified memory counts toward this requirement.
Can I run DeepSeek V4 Pro (Withdrawn Listings) on an RTX 4090 (24 GB)?
DeepSeek V4 Pro (Withdrawn Listings)'s smallest variant needs about 967 GB, which exceeds a single RTX 4090 (24 GB).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What quantization should I use for DeepSeek V4 Pro (Withdrawn Listings)?
Q4_K_M is the best balance of quality and VRAM for DeepSeek V4 Pro (Withdrawn Listings) in most cases.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How do I run DeepSeek V4 Pro (Withdrawn Listings) with Ollama?
Install Ollama, then run: ollama run deepseek-v4-pro:latest. This downloads DeepSeek V4 Pro (Withdrawn Listings) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.