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 task‑critical 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: β€œ12B” 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 reasoning‑centric variant of Qwen3.6‑27B with Multi‑Token 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 Qwen3.6‑27B backbone with strong general‑purpose capabilities

Cortiq_qwopus_dev inherits these strengths and then further specializes them via CORTIQ toward coding + agentic / tool‑use scenarios.


CORTIQ Compression

CORTIQ is a dynamic, task‑guided compression pipeline designed to retain reasoning and coding ability under strong parameter reduction:

  1. Task‑guided pruning – importance is measured under code‑centric workloads; pruning focuses on preserving coding and reasoning subspaces.
  2. Catastrophic forgetting prevention – regularization and replay prevent collapse of instruction‑following and general reasoning during compression.
  3. Layer‑wise adaptation – pruning ratios differ per layer/head based on activation statistics instead of a uniform global threshold.

The result is a ~12B‑effective 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 natural‑language specs
  • Code completion and in‑editor assistance
  • Debugging and error analysis (explain exceptions, suggest fixes)
  • DevOps / infra automation (scripts, configs, runbooks)
  • Code explanation for education / documentation
  • Tool‑use / function calling in coding agents

Target stacks include (but are not limited to): Python, JavaScript/TypeScript, C/C++, Rust, Go, Java, SQL, Bash, and infrastructure‑as‑code ecosystems.


Usage

llama.cpp

Instructions below come from the Hugging Face β€œlocal apps” 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‚ Ρ‚Π°ΠΊΠΆΠ΅ бСрётся Π½Π°ΠΏΡ€ΡΠΌΡƒΡŽ ΠΈΠ· страницы 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΄Ρ€ΡƒΠ³ΠΈΠ΅ ΠΊΠ»ΠΈΠ΅Π½Ρ‚Ρ‹

МодСль ΡƒΠΆΠ΅ ΠΈΠ½Ρ‚Π΅Π³Ρ€ΠΈΡ€ΠΎΠ²Π°Π½Π° Π² стандартныС β€œlocal apps” Hugging Face (LLM Studio, Jan, Unsloth, Pi, Hermes Agent, Docker Model Runner, Lemonade ΠΈ Π΄Ρ€.), ΠΈ ΠΌΠΎΠΆΠ΅Ρ‚ Π±Ρ‹Ρ‚ΡŒ Π²Ρ‹Π±Ρ€Π°Π½Π° поиском ΠΏΠΎ ΠΈΠΌΠ΅Π½ΠΈ infosave/cortiq_qwopus_dev [page:1].


Limitations

  • МодСль спСциализирована ΠΏΠΎΠ΄ ΠΊΠΎΠ΄ ΠΈ Π°Π³Π΅Π½Ρ‚Π½Ρ‹Π΅ сцСнарии; для чисто β€œΠΎΠ±Ρ‰Π΅Ρ‡Π°Ρ‚ΠΎΠ²Ρ‹Ρ…β€ Π·Π°Π΄Π°Ρ‡ Π½Π΅ΠΎΠ±ΡΠ·Π°Ρ‚Π΅Π»ΡŒΠ½ΠΎ Π±ΡƒΠ΄Π΅Ρ‚ ΠΎΠΏΡ‚ΠΈΠΌΠ°Π»ΡŒΠ½Π°.
  • ΠšΡ€Π°ΠΉΠ½Π΅ Π΄Π»ΠΈΠ½Π½Ρ‹ΠΉ контСкст с мноТСством Ρ„Π°ΠΉΠ»ΠΎΠ² ΠΈ инструкций ΠΌΠΎΠΆΠ΅Ρ‚ ΡƒΡ…ΡƒΠ΄ΡˆΠ°Ρ‚ΡŒ качСство Π³Π΅Π½Π΅Ρ€Π°Ρ†ΠΈΠΈ.
  • НС ΠΏΡ€Π΅Π΄Π½Π°Π·Π½Π°Ρ‡Π΅Π½Π° для Ρ„ΠΎΡ€ΠΌΠ°Π»ΡŒΠ½ΠΎ Π²Π΅Ρ€ΠΈΡ„ΠΈΡ†ΠΈΡ€ΠΎΠ²Π°Π½Π½ΠΎΠΉ ΠΈΠ»ΠΈ safety‑critical Ρ€Π°Π·Ρ€Π°Π±ΠΎΡ‚ΠΊΠΈ; всСгда провСряйтС Π²Ρ‹Π²ΠΎΠ΄ ΠΏΠ΅Ρ€Π΅Π΄ использованиСм Π² ΠΏΡ€ΠΎΠ΄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 patent‑pending. 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
Safetensors
Model size
15B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for infosave/cortiq_qwopus_dev

Base model

Qwen/Qwen3.6-27B
Quantized
(4)
this model

Collection including infosave/cortiq_qwopus_dev