Will this model run on your hardware?
Can I run DeepSeek: DeepSeek V3.2 locally?
- 685B parameters (55B active, MoE)
- context up to 160K
- licence: mit
- Weights: deepseek-ai/DeepSeek-V3.2 · GGUF: unsloth/DeepSeek-V3.2-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 713.3 GB |
| Q6_K | 551.3 GB |
| Q5_K_M | 476.2 GB |
| Q4_K_M | 405.4 GB |
| Q3_K_M | 320.2 GB |
| Q2_K | 245.4 GB |
Run it locally
ollama run hf.co/unsloth/DeepSeek-V3.2-GGUF:Q4_K_M
llama serve -hf unsloth/DeepSeek-V3.2-GGUF:Q4_K_M
LM Studio: open unsloth/DeepSeek-V3.2-GGUF