Instructions to use unsloth/DeepSeek-V3.1-Terminus-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/DeepSeek-V3.1-Terminus-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/DeepSeek-V3.1-Terminus-GGUF",
	filename="BF16/DeepSeek-V3.1-Terminus-BF16-00001-of-00030.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-V3.1-Terminus-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-V3.1-Terminus-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/DeepSeek-V3.1-Terminus-GGUF to start chatting

Docker Model Runner
How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-V3.1-Terminus-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-V3.1-Terminus-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-V3.1-Terminus-GGUF-UD-Q4_K_XL

List all available models

lemonade list

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

DeepSeek-V3.1-Terminus

Introduction

This update maintains the model's original capabilities while addressing issues reported by users, including:

Language consistency: Reducing instances of mixed Chinese-English text and occasional abnormal characters;
Agent capabilities: Further optimizing the performance of the Code Agent and Search Agent.

Benchmark	DeepSeek-V3.1	DeepSeek-V3.1-Terminus
Reasoning Mode w/o Tool Use
MMLU-Pro	84.8	85.0
GPQA-Diamond	80.1	80.7
Humanity's Last Exam	15.9	21.7
LiveCodeBench	74.8	74.9
Codeforces	2091	2046
Aider-Polyglot	76.3	76.1
Agentic Tool Use
BrowseComp	30.0	38.5
BrowseComp-zh	49.2	45.0
SimpleQA	93.4	96.8
SWE Verified	66.0	68.4
SWE-bench Multilingual	54.5	57.8
Terminal-bench	31.3	36.7

The template and tool-set of search agent have been updated, which is shown in assets/search_tool_trajectory.html.

How to Run Locally

The model structure of DeepSeek-V3.1-Terminus is the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

For the model's chat template other than search agent, please refer to the DeepSeek-V3.1 repo.

Here we also provide an updated inference demo code in the inference folder to help the community get started with running our model and understand the details of model architecture.

NOTE: In the current model checkpoint, the parameters of self_attn.o_proj do not conform to the UE8M0 FP8 scale data format. This is a known issue and will be corrected in future model releases.

License

This repository and the model weights are licensed under the MIT License.

Citation

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}