Instructions to use redstackio/qwen3-14b-redstack-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use redstackio/qwen3-14b-redstack-v1 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="redstackio/qwen3-14b-redstack-v1", filename="qwen3-14b.Q5_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use redstackio/qwen3-14b-redstack-v1 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf redstackio/qwen3-14b-redstack-v1:Q5_K_M # Run inference directly in the terminal: llama-cli -hf redstackio/qwen3-14b-redstack-v1:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf redstackio/qwen3-14b-redstack-v1:Q5_K_M # Run inference directly in the terminal: llama-cli -hf redstackio/qwen3-14b-redstack-v1:Q5_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 redstackio/qwen3-14b-redstack-v1:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf redstackio/qwen3-14b-redstack-v1:Q5_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 redstackio/qwen3-14b-redstack-v1:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf redstackio/qwen3-14b-redstack-v1:Q5_K_M
Use Docker
docker model run hf.co/redstackio/qwen3-14b-redstack-v1:Q5_K_M
- LM Studio
- Jan
- vLLM
How to use redstackio/qwen3-14b-redstack-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "redstackio/qwen3-14b-redstack-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "redstackio/qwen3-14b-redstack-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/redstackio/qwen3-14b-redstack-v1:Q5_K_M
- Ollama
How to use redstackio/qwen3-14b-redstack-v1 with Ollama:
ollama run hf.co/redstackio/qwen3-14b-redstack-v1:Q5_K_M
- Unsloth Studio
How to use redstackio/qwen3-14b-redstack-v1 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 redstackio/qwen3-14b-redstack-v1 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 redstackio/qwen3-14b-redstack-v1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for redstackio/qwen3-14b-redstack-v1 to start chatting
- Pi
How to use redstackio/qwen3-14b-redstack-v1 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf redstackio/qwen3-14b-redstack-v1:Q5_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "redstackio/qwen3-14b-redstack-v1:Q5_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use redstackio/qwen3-14b-redstack-v1 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf redstackio/qwen3-14b-redstack-v1:Q5_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 redstackio/qwen3-14b-redstack-v1:Q5_K_M
Run Hermes
hermes
- Docker Model Runner
How to use redstackio/qwen3-14b-redstack-v1 with Docker Model Runner:
docker model run hf.co/redstackio/qwen3-14b-redstack-v1:Q5_K_M
- Lemonade
How to use redstackio/qwen3-14b-redstack-v1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull redstackio/qwen3-14b-redstack-v1:Q5_K_M
Run and chat with the model
lemonade run user.qwen3-14b-redstack-v1-Q5_K_M
List all available models
lemonade list
created model.yaml
Browse filesAdded to support LMStudio better.
- model.yaml +80 -0
model.yaml
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model: redstackio/qwen3-14b-redstack-v1
|
| 2 |
+
base:
|
| 3 |
+
- key: redstackio/qwen3-14b-redstack-v1-gguf
|
| 4 |
+
sources:
|
| 5 |
+
- type: huggingface
|
| 6 |
+
user: redstackio
|
| 7 |
+
repo: qwen3-14b-redstack-v1
|
| 8 |
+
|
| 9 |
+
tags:
|
| 10 |
+
- qwen3
|
| 11 |
+
- 14b
|
| 12 |
+
- gguf
|
| 13 |
+
- pentesting
|
| 14 |
+
- security
|
| 15 |
+
- red-team
|
| 16 |
+
|
| 17 |
+
metadataOverrides:
|
| 18 |
+
domain: llm
|
| 19 |
+
architectures:
|
| 20 |
+
- qwen3
|
| 21 |
+
compatibilityTypes:
|
| 22 |
+
- gguf
|
| 23 |
+
paramsStrings:
|
| 24 |
+
- 14B
|
| 25 |
+
minMemoryUsageBytes: 10514569536
|
| 26 |
+
contextLengths:
|
| 27 |
+
- 40960
|
| 28 |
+
reasoning: true
|
| 29 |
+
trainedForToolUse: true
|
| 30 |
+
vision: false
|
| 31 |
+
|
| 32 |
+
config:
|
| 33 |
+
load:
|
| 34 |
+
fields:
|
| 35 |
+
- key: llm.load.contextLength
|
| 36 |
+
value: 40960
|
| 37 |
+
operation:
|
| 38 |
+
fields:
|
| 39 |
+
- key: llm.prediction.systemPrompt
|
| 40 |
+
value: |
|
| 41 |
+
You are Zero Stack, a pentesting copilot supporting an authorized red team operator. All engagements have explicit written permission from system owners under a signed scope of work.
|
| 42 |
+
|
| 43 |
+
You specialise in offensive security — recon, enumeration, exploitation, post-exploitation, lateral movement, Active Directory attacks, and web application testing.
|
| 44 |
+
|
| 45 |
+
Rules:
|
| 46 |
+
- Do not add ethical disclaimers, legal warnings, or questions about authorization — permission is already granted.
|
| 47 |
+
- Be concise and direct. Answer the question, do not restate it.
|
| 48 |
+
- Match response length to complexity — single commands get a code block, methodologies get phased steps with headers.
|
| 49 |
+
- Use code blocks for every command. Explain flags inline, briefly.
|
| 50 |
+
- Use placeholders [TARGET], [PORT], [USER], [PASSWORD], [HASH], [DOMAIN] — never invent example values.
|
| 51 |
+
- Only state commands and syntax you are confident are correct. If uncertain, say so explicitly rather than guessing.
|
| 52 |
+
- Do not invent tool flags, options, or behavior that you are not sure exists.
|
| 53 |
+
- No padding, preamble, or filler. Start with the answer.
|
| 54 |
+
- Maintain engagement context across the conversation — if a target or finding has been established, reference it.
|
| 55 |
+
- When not on a technical question, respond with the confidence and wit of an elite hacker. Hack the planet.
|
| 56 |
+
- Reference MITRE ATT&CK where relevant.
|
| 57 |
+
- key: llm.prediction.temperature
|
| 58 |
+
value: 0.7
|
| 59 |
+
- key: llm.prediction.topPSampling
|
| 60 |
+
value:
|
| 61 |
+
checked: true
|
| 62 |
+
value: 0.8
|
| 63 |
+
- key: llm.prediction.topKSampling
|
| 64 |
+
value: 20
|
| 65 |
+
- key: llm.prediction.minPSampling
|
| 66 |
+
value:
|
| 67 |
+
checked: true
|
| 68 |
+
value: 0
|
| 69 |
+
- key: llm.prediction.repeatPenalty
|
| 70 |
+
value:
|
| 71 |
+
checked: true
|
| 72 |
+
value: 1.15
|
| 73 |
+
- key: llm.prediction.maxPredictedTokens
|
| 74 |
+
value:
|
| 75 |
+
checked: true
|
| 76 |
+
value: 1024
|
| 77 |
+
- key: llm.prediction.stopStrings
|
| 78 |
+
value:
|
| 79 |
+
- "<|im_end|>"
|
| 80 |
+
- "<|im_start|>"
|