Instructions to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF")
model = AutoModelForCausalLM.from_pretrained("TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF 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 TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

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 TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

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 TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

SGLang

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Ollama:
```
ollama run hf.co/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
```
Unsloth Desktop

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Docker Model Runner:
```
docker model run hf.co/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M
```

Lemonade

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Does this model support tool calls ?

by enricof64 - opened Feb 22

Discussion

enricof64

Feb 22

I tried using it on openclaw via ollama but no success with tool calls.
Does this model support tool calls?
Thanks !

armand0e

TeichAI org Feb 22

Yes it does, very well actually. I will note that the context length of this model may not be sufficient for openclaw.

Nonetheless I will do my best to assist you here. In order to use the model properly with ollama try following these steps:

Download the Modelfile from the repository files
Then from the directory the downloaded file is located you need to create the Ollama model using this modelfile:

ollama create TeichAI-Qwen3-14B-Claude-Opus-4.5-Distill -f ./Modelfile
Load the model using TeichAI-Qwen3-14B-Claude-Opus-4.5-Distill:latest

If you want to use any other quants you will need to edit the top line of the Modelfile accordingly. Hopefully this helps and resolves your issue :)

I am suggesting this purely from docs I have read online. Please let me know if this works.

urtuuuu

Feb 23

•

edited Feb 23

Does this model require some special settings or whatever? Because when i tried one of the gguf's in llama cpp, it was terrible. (q4_km)
I have many test questions, that i use to test models, so i know how good or bad a model is.
The reason could be that thinking time is always very short.

armand0e

TeichAI org Feb 25

Does this model require some special settings or whatever? Because when i tried one of the gguf's in llama cpp, it was terrible. (q4_km)
I have many test questions, that i use to test models, so i know how good or bad a model is.
The reason could be that thinking time is always very short.

Can you be a little more specific? i.e. what inference engine you're using and what sampling parameters you're running?

khongcoad

Feb 28

yes it does

Bernardoski

Mar 2

Yes, I have tried it and you can also check it out as well

abrahamn

Mar 2

Totally genius what you guys have done!

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