DeepSeek V3.2-Exp — local AI model by DeepSeek
Written by Jakub Rusinowski · Last updated
DeepSeek-V3.2-Exp, the experimental sparse-attention snapshot released in September 2025 ahead of the V3.2 line.
Variants
The smallest DeepSeek V3.2-Exp 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 V3.2-Exp 685B 685B (37B active) | ~414.4 GB | 128,000 | ollama run deepseek-v3-2-exp |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run DeepSeek V3.2-Exp locally
Install Ollama, then pull the tag.
ollama run deepseek-v3-2-expPick 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 V3.2-Exp 685BDeepSeek V3.2-Exp — frequently asked questions
How much VRAM does DeepSeek V3.2-Exp need?
DeepSeek V3.2-Exp needs about 414 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek V3.2-Exp 685B (414 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run DeepSeek V3.2-Exp on an RTX 4090 (24 GB)?
DeepSeek V3.2-Exp'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 V3.2-Exp?
Q4_K_M is the best balance of quality and VRAM for DeepSeek V3.2-Exp 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 V3.2-Exp with Ollama?
DeepSeek V3.2-Exp has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.