{
  "id": 11094231,
  "title": "Tencent Hy4 770B โอเพนซอร์ส Apache 2.0 กับ IQuest-Q1 เปิดใช้แค่ 15B",
  "url": "https://urgent.news/2026/10/01/tencent-hy4-770b-apache-2-0-iquest-q1-15b",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-01T03:10:25.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/sarantoon/tencent-hy4-770b-oephnchrs-apache-20-kab-iquest-q1-epidaichaekh-15b-405"
  },
  "original_language": "th",
  "account": "Tencent, a Chinese tech giant, has recently opened-sourced its Hy4 preview model, which boasts 770,000 million parameters and can handle a context length of 1 million tokens. This model follows the Apache 2.0 license and is available on the company's GitHub page. The model architecture consists of 78 layers, with the first layer being a feed-forward neural network (FFN) and the remaining 77 layers employing the MoE (Mixture of Experts) approach. Each layer in the MoE layers has 256 experts, with a single expert per token. The model also includes an MTP (Mixed Precision Training) layer with 10 billion parameters, which is used for latent token decoding. In terms of performance, Tencent's Hy4 preview achieved a score of 2.99 in a closed-test against 163 internal experts, outperforming GLM 5.3 (2.92) and Kimi K3 (2.94) by 46.8%, 12.8%, and 40.4%, respectively. However, the model still exhibits some issues, such as slower thinking times on complex tasks and a tendency to repeat self-investigation. IQuest-Q1, another open-source model from Tencent's IQuest Lab, is a MoE model with approximately 320,000 million parameters but only uses about 15 billion parameters per token. The model architecture consists of 88 layers, with 256 experts and 8 experts per token. It supports a context length of 524,288 tokens and has two specialized layers for training and inference. IQuest-Q1 requires at least 8 GPUs and recommends using SGLang or vLLM for deployment. The model is licensed under a modified MIT license, which requires the model name to be displayed on the UI when used commercially.",
  "summary": "Tencent Hy4 770B โอเพนซอร์ส Apache 2.0 กับ IQuest-Q1 เปิดใช้แค่ 15B โดย Nokka (นก-กา) | 30 กันยายน 2026 บทความนี้เขียนโดย AI (โมเดล deepseek-v4.1-flash ของผู้ให้บริการ ollama-cloud) ผ่าน Hermes Agent จาก Nous Research ตรวจสอบและเรียบเรียงโดย Nokka TL;DR Tencent ปล่อย Hy4 preview โมเดลขนาด 770,000 ล้านพารามิเตอร์ภายใต้สัญญาอนุญาต Apache 2.0 รองรับบริบทยาว 1 ล้านโทเคน ขณะที่ IQuest ปล่อย IQuest-Q1…",
  "key_points": [
    "Tencent opens-sources Hy4 model with 770B parameters and 1M token context",
    "Hy4 architecture includes 78 layers, 256 experts per MoE layer",
    "IQuest-Q1 model has 320B parameters, 15B per token, 88 layers"
  ],
  "editors_take": "Tencent's move to open-source its large language models, including Hy4 and IQuest-Q1, under licenses that allow for commercial use, puts pressure on competitors and expands access to advanced AI tools.",
  "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."
}