DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp is an open-weights language model from DeepSeek, released September 29, 2025. It has 685B parameters (mixture-of-experts, 52B active). The context window is 160K tokens. On the Epoch Capabilities Index it scores 144.4, rank 98 of 256 rated models.
We are excited to announce the official release of DeepSeek-V3.2-Exp, an experimental version of our model. As an intermediate step toward our next-generation architecture, V3.2-Exp builds upon V3.1-Terminus by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate …
Check it against your own PC →
Can you run DeepSeek-V3.2-Exp locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| Aider Polyglot | 74.2% |
| The Agent Company | 42.9% |
Links
Announcement · Hugging Face: deepseek-ai/DeepSeek-V3.2-Exp-Base · Epoch AI benchmarks
Models with a similar score
Qwen3.5 397B-A17B · Qwen3.7-Plus · MiniMax-M3 · Claude Sonnet 4.5 · o3-pro · Qwen 3.5 Plus (hosted 397B-A17B) · o3 · Nemotron 3 Ultra
More from DeepSeek
DeepSeek V4.1 Flash 1017 · DeepSeek V4 Flash Vision Exp · DeepSeek V4.1 Flash · DeepSeek V4 Pro 0813 · DeepSeek V4 Flash 0731 · DeepSeek V4 Pro DSpark · DeepSeek V4 Flash DSpark · DeepSeek-V4-Pro