Instructions to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
# Run inference directly in the terminal:
llama cli -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
# Run inference directly in the terminal:
llama cli -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

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 anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
# Run inference directly in the terminal:
./llama-cli -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

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 anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

Use Docker

docker model run hf.co/anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

LM Studio
Jan

vLLM

How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anikifoss/DeepSeek-V3.1-Terminus-HQ4_K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anikifoss/DeepSeek-V3.1-Terminus-HQ4_K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

Ollama
How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with Ollama:
```
ollama run hf.co/anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
```

Unsloth Studio

How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K 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 anikifoss/DeepSeek-V3.1-Terminus-HQ4_K 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 anikifoss/DeepSeek-V3.1-Terminus-HQ4_K to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anikifoss/DeepSeek-V3.1-Terminus-HQ4_K to start chatting

Docker Model Runner
How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with Docker Model Runner:
```
docker model run hf.co/anikifoss/DeepSeek-V3.1-Terminus-HQ4_K
```

Lemonade

How to use anikifoss/DeepSeek-V3.1-Terminus-HQ4_K with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anikifoss/DeepSeek-V3.1-Terminus-HQ4_K

Run and chat with the model

lemonade run user.DeepSeek-V3.1-Terminus-HQ4_K-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Missing <think> tags

by sousekd - opened Nov 10, 2025

Discussion

sousekd

Nov 10, 2025

•

edited Nov 10, 2025

Currently llama.cpp does not return <think> token in response. If you know how to fix that, please share in the "Community" section!

I was researching the reasoning formatting issues of Kimi-K2-Thinking and found this llama.cpp param:

-sp,   --special                        special tokens output enabled (default: false)

@unsloth mentions it here:
https://docs.unsloth.ai/models/kimi-k2-thinking-how-to-run-locally

I did not have a chance to test it yet, but I am quite positive it might help :).

anikifoss

Owner Nov 28, 2025

•

edited Nov 28, 2025

Thanks, I tried --special with PrimeIntellect_INTELLECT-3-Q8_0, but it didn't work. I'll try it with some other models as well.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment