{
  "id": 20159437,
  "title": "ZQN-12B: our second open model, plus the M3-GPTQ compression paper",
  "url": "https://urgent.news/2026/11/15/zqn-12b-our-second-open-model-plus-the-m3-gptq-compression-paper",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-15T10:44:32.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/zaqeris_ai/zqn-12b-our-second-open-model-plus-the-m3-gptq-compression-paper-30o8"
  },
  "original_language": "en",
  "account": "ZAQERIS Ai, an independent AI research group based in Cairo, Egypt, has released ZQN-12B, their second open model. This model is built from scratch using 15.55B parameters and has been compressed with the ZAQERIS M3-GPTQ method to a size of 6.48 GiB, or 3.25 bits per weight. The compressed model can run on a consumer GPU with an 8 GB memory capacity, achieving approximately 25 tokens per second. The model offers a 128K native context window, which can be expanded to 256K using a technique called YaRN.\n\nAlongside the release of the model, ZAQERIS Ai published a technical paper detailing the compression method used to achieve such a compact size. The paper, titled \"ZAQERIS M3-GPTQ: Hessian-Aware Multi-Stage Residual Vector Quantization for Extreme Bitrate LLM Compression,\" outlines a comprehensive approach to LLM (Language Model) compression. This method combines Block-Hadamard decorrelation, Hessian-salience outlier selection, multi-stage 8-dimensional residual vector quantization, and Block-8 Cholesky GPTQ error propagation techniques. The full technical paper can be accessed at https://huggingface.co/ZAQERIS/ZQN-12B/blob/main/docs/papers/ZAQERIS_M3_GPTQ_PAPER.md.\n\nIt is important to note that ZQN-12B is an early checkpoint model, not a frontier model, and the researchers have been transparent about its limitations. This information is clearly stated on the model card, which is available at https://huggingface.co/ZAQERIS/ZQN-12B. The researchers welcome feedback and contributions from the community to further improve and develop this open model.",
  "summary": "ZQN-12B is the second open model from ZAQERIS Ai, an independent AI research group in Cairo, Egypt. Trained from scratch 15.55B parameters, compressed with our ZAQERIS M3-GPTQ method to 6.48 GiB (3.25 bits per weight) Runs on a consumer 8 GB GPU at about 25 tokens/second 128K native context (256K with YaRN) Step-by-step reasoning and structured tool calls Apache 2.0 Model:…",
  "key_points": [
    "ZQAERIS Ai releases ZQN-12B, their second open model with 15.55B parameters.",
    "Model compressed to 6.48 GiB using ZAQERIS M3-GPTQ compression method.",
    "ZQN-12B offers 128K context window, expandable to 256K with YaRN technique."
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}