Instructions to use infosave/cortiq_qwopus_dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/cortiq_qwopus_dev with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/cortiq_qwopus_dev --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq run FILE.cmf --prompt "What is the capital of France?"
cortiq serve FILE.cmf --port 8080 # OpenAI-compatible server
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use infosave/cortiq_qwopus_dev 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 infosave/cortiq_qwopus_dev:Q4_K_M # Run inference directly in the terminal: llama cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf infosave/cortiq_qwopus_dev:Q4_K_M # Run inference directly in the terminal: llama cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf infosave/cortiq_qwopus_dev:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Use Docker
docker model run hf.co/infosave/cortiq_qwopus_dev:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use infosave/cortiq_qwopus_dev with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "infosave/cortiq_qwopus_dev" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "infosave/cortiq_qwopus_dev", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/infosave/cortiq_qwopus_dev:Q4_K_M
- Ollama
How to use infosave/cortiq_qwopus_dev with Ollama:
ollama run hf.co/infosave/cortiq_qwopus_dev:Q4_K_M
- Unsloth Desktop
- Pi
How to use infosave/cortiq_qwopus_dev with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf infosave/cortiq_qwopus_dev: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "infosave/cortiq_qwopus_dev:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use infosave/cortiq_qwopus_dev with Docker Model Runner:
docker model run hf.co/infosave/cortiq_qwopus_dev:Q4_K_M
- Lemonade
How to use infosave/cortiq_qwopus_dev with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull infosave/cortiq_qwopus_dev:Q4_K_M
Run and chat with the model
lemonade run user.cortiq_qwopus_dev-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use infosave/cortiq_qwopus_dev with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf infosave/cortiq_qwopus_dev: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://127.0.0.1:9931/v1 hermes config set model.default infosave/cortiq_qwopus_dev:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use infosave/cortiq_qwopus_dev with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf infosave/cortiq_qwopus_dev: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://127.0.0.1:9931/v1 \ --custom-model-id "infosave/cortiq_qwopus_dev: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"
Cortiq_qwopus_dev
Cortiq_qwopus_dev 12B is a task-specialized coding model compiled from
Jackrong/Qwopus3.6-27B-v2-MTP-GGUF,
a Multi-Token Prediction (MTP) reasoning model ultimately derived from
Qwen3.6-27B.
The original 27B model is compressed down to an effective ~12B parameters using a proprietary dynamic neural network compression method developed by AllAIGate.
The compression is performed via the CORTIQ method β a system and method for Dynamic Task-Guided Neural Network Compression with Catastrophic Forgetting Prevention, covered under US Patent Application No. 19/452,464 (filed January 19, 2026).
Unlike naive pruning or pure quantization, CORTIQ preserves taskβcritical knowledge during compression by dynamically guiding the pruning process toward the target domain (code generation / agentic coding), while actively preventing degradation of the model's core reasoning capabilities.
Model Details
| Property | Value |
|---|---|
| Repository | infosave/cortiq_qwopus_dev |
| Format(s) | Safetensors, GGUF |
| GGUF filename | qwopus-nvg-12b-F16.gguf |
| Base model | Qwopus3.6-27B-v2-MTP-GGUF |
| Base root | Qwen3.6-27B |
| Architecture | qwen3_5_text (decoder-only transformer) |
| Model size | ~15B stored params (BF16) |
| Effective size | ~12B parameters after CORTIQ compression |
| Tensor type | BF16 |
| License | MIT |
| Compression | CORTIQ (Dynamic Task-Guided Compression + CF prevention) |
| Developer | AllAIGate |
Note: β12Bβ refers to the effective parameter budget of the compressed topology; Hugging Face reports ~15B stored BF16 parameters for this checkpoint.
Why Qwopus3.6-27B-v2-MTP as Base?
Qwopus3.6-27B-v2-MTP is a reasoningβcentric variant of Qwen3.6β27B with
MultiβToken Prediction and dedicated alignment for reasoning, coding,
DevOps, and math. It already incorporates:
- MTP speculative decoding for higher throughput on long sequences
- Training focused on structured reasoning and code / math workflows
- A Qwen3.6β27B backbone with strong generalβpurpose capabilities
Cortiq_qwopus_dev inherits these strengths and then further specializes them via CORTIQ toward coding + agentic / toolβuse scenarios.
CORTIQ Compression
CORTIQ is a dynamic, taskβguided compression pipeline designed to retain reasoning and coding ability under strong parameter reduction:
- Taskβguided pruning β importance is measured under codeβcentric workloads; pruning focuses on preserving coding and reasoning subspaces.
- Catastrophic forgetting prevention β regularization and replay prevent collapse of instructionβfollowing and general reasoning during compression.
- Layerβwise adaptation β pruning ratios differ per layer/head based on activation statistics instead of a uniform global threshold.
The result is a ~12Bβeffective model with significantly lower memory and better latency compared to the original 27B model, while keeping most of its coding and reasoning performance.
Intended Use
Cortiq_qwopus_dev is designed primarily for agentic coding workflows:
- Code generation (functions, classes, modules) from naturalβlanguage specs
- Code completion and inβeditor assistance
- Debugging and error analysis (explain exceptions, suggest fixes)
- DevOps / infra automation (scripts, configs, runbooks)
- Code explanation for education / documentation
- Toolβuse / function calling in coding agents
Target stacks include (but are not limited to): Python, JavaScript/TypeScript, C/C++, Rust, Go, Java, SQL, Bash, and infrastructureβasβcode ecosystems.
Usage
llama.cpp
Instructions below come from the Hugging Face βlocal appsβ integration for
infosave/cortiq_qwopus_dev [page:1].
# Install via Homebrew (macOS / Linux)
brew install llama.cpp
# Start a local OpenAI-compatible server with web UI:
llama-server -hf infosave/cortiq_qwopus_dev:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Windows (WinGet):
winget install llama.cpp
# Server:
llama-server -hf infosave/cortiq_qwopus_dev:Q4_K_M
# CLI:
llama-cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Prebuilt binary (GitHub releases of llama.cpp):
./llama-server -hf infosave/cortiq_qwopus_dev:Q4_K_M
./llama-cli -hf infosave/cortiq_qwopus_dev:Q4_K_M
Python (llama-cpp-python)
Π‘Π½ΠΈΠΏΠΏΠ΅Ρ ΡΠ°ΠΊΠΆΠ΅ Π±Π΅ΡΡΡΡΡ Π½Π°ΠΏΡΡΠΌΡΡ ΠΈΠ· ΡΡΡΠ°Π½ΠΈΡΡ ΠΌΠΎΠ΄Π΅Π»ΠΈ [page:1]:
# pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="infosave/cortiq_qwopus_dev",
filename="qwopus-nvg-12b-F16.gguf",
)
resp = llm.create_chat_completion(
messages=[
{"role": "user", "content": "Write a Python quicksort implementation."}
]
)
print(resp["choices"]["message"]["content"])
Ollama
ollama run hf.co/infosave/cortiq_qwopus_dev:Q4_K_M
LM Studio / Jan / Unsloth / Π΄ΡΡΠ³ΠΈΠ΅ ΠΊΠ»ΠΈΠ΅Π½ΡΡ
ΠΠΎΠ΄Π΅Π»Ρ ΡΠΆΠ΅ ΠΈΠ½ΡΠ΅Π³ΡΠΈΡΠΎΠ²Π°Π½Π° Π² ΡΡΠ°Π½Π΄Π°ΡΡΠ½ΡΠ΅ βlocal appsβ Hugging Face
(LLM Studio, Jan, Unsloth, Pi, Hermes Agent, Docker Model Runner, Lemonade ΠΈ Π΄Ρ.),
ΠΈ ΠΌΠΎΠΆΠ΅Ρ Π±ΡΡΡ Π²ΡΠ±ΡΠ°Π½Π° ΠΏΠΎΠΈΡΠΊΠΎΠΌ ΠΏΠΎ ΠΈΠΌΠ΅Π½ΠΈ infosave/cortiq_qwopus_dev [page:1].
Limitations
- ΠΠΎΠ΄Π΅Π»Ρ ΡΠΏΠ΅ΡΠΈΠ°Π»ΠΈΠ·ΠΈΡΠΎΠ²Π°Π½Π° ΠΏΠΎΠ΄ ΠΊΠΎΠ΄ ΠΈ Π°Π³Π΅Π½ΡΠ½ΡΠ΅ ΡΡΠ΅Π½Π°ΡΠΈΠΈ; Π΄Π»Ρ ΡΠΈΡΡΠΎ βΠΎΠ±ΡΠ΅ΡΠ°ΡΠΎΠ²ΡΡ β Π·Π°Π΄Π°Ρ Π½Π΅ΠΎΠ±ΡΠ·Π°ΡΠ΅Π»ΡΠ½ΠΎ Π±ΡΠ΄Π΅Ρ ΠΎΠΏΡΠΈΠΌΠ°Π»ΡΠ½Π°.
- ΠΡΠ°ΠΉΠ½Π΅ Π΄Π»ΠΈΠ½Π½ΡΠΉ ΠΊΠΎΠ½ΡΠ΅ΠΊΡΡ Ρ ΠΌΠ½ΠΎΠΆΠ΅ΡΡΠ²ΠΎΠΌ ΡΠ°ΠΉΠ»ΠΎΠ² ΠΈ ΠΈΠ½ΡΡΡΡΠΊΡΠΈΠΉ ΠΌΠΎΠΆΠ΅Ρ ΡΡ ΡΠ΄ΡΠ°ΡΡ ΠΊΠ°ΡΠ΅ΡΡΠ²ΠΎ Π³Π΅Π½Π΅ΡΠ°ΡΠΈΠΈ.
- ΠΠ΅ ΠΏΡΠ΅Π΄Π½Π°Π·Π½Π°ΡΠ΅Π½Π° Π΄Π»Ρ ΡΠΎΡΠΌΠ°Π»ΡΠ½ΠΎ Π²Π΅ΡΠΈΡΠΈΡΠΈΡΠΎΠ²Π°Π½Π½ΠΎΠΉ ΠΈΠ»ΠΈ safetyβcritical ΡΠ°Π·ΡΠ°Π±ΠΎΡΠΊΠΈ; Π²ΡΠ΅Π³Π΄Π° ΠΏΡΠΎΠ²Π΅ΡΡΠΉΡΠ΅ Π²ΡΠ²ΠΎΠ΄ ΠΏΠ΅ΡΠ΅Π΄ ΠΈΡΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°Π½ΠΈΠ΅ΠΌ Π² ΠΏΡΠΎΠ΄Π΅.
License
This model is released under the MIT License (as specified on the model page). [page:1]
The underlying CORTIQ compression method is proprietary and patentβpending. Commercial use of the weights follows MIT; separate licensing may be required for direct use of the CORTIQ pipeline itself.
Citation
@misc{allaigate2026cortiq_qwopus_dev,
title = {Cortiq\_qwopus\_dev 12B:
Task-Specialized Coding via Dynamic Compression
from Qwopus3.6-27B-v2-MTP},
author = {AllAIGate},
year = {2026},
howpublished = {\url{https://huggingface.co/infosave/cortiq_qwopus_dev}},
note = {Base: Jackrong/Qwopus3.6-27B-v2-MTP-GGUF.
CORTIQ method: US Patent Application No. 19/452,464}
}
- Downloads last month
- 210