---
license: mit
library_name: transformers
base_model:
- deepseek-ai/DeepSeek-V3.1-Terminus
---
Learn how to run DeepSeek-V3.1 Terminus correctly - Read our Guide.
See how DeepSeek-V3.1 Dynamic 3-bit GGUF scores 75.6% on Aider Polyglot here.
🐋 DeepSeek-V3.1-Terminus Usage Guidelines
These quants include our Unsloth chat template fixes, specifically for llama.cpp supported backends.
- You must use --jinja for llama.cpp quants
- Set the temperature **~0.6** (recommended) and Top_P value of **0.95** (recommended)
- UD-Q2_K_XL (247GB) is recommended
- For complete detailed instructions, see our guide: [unsloth.ai/blog/deepseek-v3.1](https://docs.unsloth.ai/basics/deepseek-v3.1)
# DeepSeek-V3.1-Terminus