{
  "source_file": "0930",
  "source_platform": "Dev.to",
  "author": "Julien Simon",
  "title_listed": "Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour!",
  "keywords": "",
  "domain": "大模型算法",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://dev.to/juliensimon/deploying-supernova-lite-on-inferentia2-the-best-8b-model-for-1-an-hour-138h",
  "publish_date": "2024-09-19",
  "corpus_stage": "",
  "notes": "",
  "id": "aa197ca3f0a2",
  "collected_at": "2026-10-02T14:00:41",
  "title": "Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour! - DEV Community",
  "body_markdown": "In this video, you will learn about\nLlama-3.1-SuperNova-Lite\n, the best open-source 8B model available today according to the\nHugging Face Open LLM Leaderboard\n.\nLlama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai, based on the Llama-3.1–8B-Instruct architecture. It is a distilled version of the larger Llama-3.1–405B-Instruct model, leveraging offline logits extracted from the 405B parameter variant. This 8B variation of Llama-3.1-SuperNova maintains high performance while offering exceptional instruction-following capabilities and domain-specific adaptability.\nI’ll show you how to compile on the fly and deploy SuperNova Lite on a SageMaker endpoint powered by an inf2.xlarge instance, the smallest Inferentia2 instance available at only $0.99 an hour!",
  "metadata": {
    "title": "Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour! - DEV Community",
    "description": "In this video, you will learn about Llama-3.1-SuperNova-Lite, the best open-source 8B model available... Tagged with opensource, ai, aws, transformers.",
    "keywords": "opensource, ai, aws, transformers, software, coding, development, engineering, inclusive, community",
    "author": null,
    "og:type": "article",
    "og:url": "https://dev.to/juliensimon/deploying-supernova-lite-on-inferentia2-the-best-8b-model-for-1-an-hour-138h",
    "og:title": "Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour!",
    "og:description": "In this video, you will learn about Llama-3.1-SuperNova-Lite, the best open-source 8B model available...",
    "og:site_name": "DEV Community",
    "og:image": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Ficnbmhep8d367f1vme0h.png",
    "twitter:site": "@thepracticaldev",
    "twitter:creator": "@julsimon",
    "twitter:title": "Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour!",
    "twitter:description": "In this video, you will learn about Llama-3.1-SuperNova-Lite, the best open-source 8B model available...",
    "twitter:card": "summary_large_image",
    "twitter:widgets:new-embed-design": "on",
    "twitter:image:src": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Ficnbmhep8d367f1vme0h.png"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fz79u2x0qj0egm8yoyxk5.png",
      "bytes": 167740,
      "reused": true,
      "local_path": "attachments/aa197ca3f0a2/images/001.png",
      "src": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fz79u2x0qj0egm8yoyxk5.png",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://www.youtube.com/watch?v=eaO_4nqrBbs",
      "src": "https://www.youtube.com/embed/eaO_4nqrBbs",
      "status": "ok",
      "kind": "single_video",
      "local_path": "attachments/aa197ca3f0a2/videos/repair-eaO_4nqrBbs.mp4",
      "bytes": 112798363,
      "valid": true,
      "height": 1080,
      "width": 1920,
      "duration": "1331.061000",
      "reused": false
    }
  ],
  "links": [
    {
      "href": "https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite",
      "label": "Llama-3.1-SuperNova-Lite",
      "type": "a"
    },
    {
      "href": "https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard",
      "label": "Hugging Face Open LLM Leaderboard",
      "type": "a"
    },
    {
      "href": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fz79u2x0qj0egm8yoyxk5.png",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.youtube.com/embed/eaO_4nqrBbs",
      "label": "",
      "type": "iframe"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:49:05Z",
  "source_url": "https://dev.to/juliensimon/deploying-supernova-lite-on-inferentia2-the-best-8b-model-for-1-an-hour-138h",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 780,
  "expected_body_images": 1,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/aa197ca3f0a2/pages/source.html",
  "local_html": "attachments/aa197ca3f0a2/pages/article.html",
  "body_base_path": "attachments/aa197ca3f0a2/pages/",
  "body_markdown_path": "attachments/aa197ca3f0a2/pages/article.md"
}