{
  "schema_version": "1.0",
  "publisher": "AI Release",
  "article": {
    "title": "Ryzen 9 8940HX and RTX 5060: Running Local LLMs on a Laptop with 8 GB of VRAM",
    "canonical_url": "https://ai-release.org/posts/ryzen-9-8940hx-i-rtx-5060-lokalnye-llm-na-noutbuke-s-8-gb-vram-e0ee9858_en.html",
    "language": "en",
    "article_type": "news",
    "published_at": "2026-11-17T00:00:00+00:00",
    "updated_at": "2026-11-17T00:00:00+00:00"
  },
  "summary": "Автор на MAIBENBEN X17F с Ryzen 9 8940HX и RTX 5060 прогнал четыре кодер-модели в Ollama и Strata: 8 ГБ VRAM, 40 ГБ ОЗУ, скрытые тесты.",
  "topics": [
    "local",
    "Ollama",
    "квантование",
    "laptops",
    "AI",
    "LLM",
    "neural networks",
    "local LLMs"
  ],
  "entities": [
    {
      "id": "E-SRC",
      "name": "habr.com",
      "type": "source",
      "description": "source domain",
      "url": "https://habr.com/ru/articles/1105358/"
    },
    {
      "id": "E-T1",
      "name": "local",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T2",
      "name": "Ollama",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T3",
      "name": "квантование",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T4",
      "name": "laptops",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T5",
      "name": "AI",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T6",
      "name": "LLM",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T7",
      "name": "neural networks",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-T8",
      "name": "local LLMs",
      "type": "topic",
      "description": "publication tag",
      "url": null
    },
    {
      "id": "E-AIR",
      "name": "AI Release",
      "type": "publisher",
      "description": "published the article",
      "url": "https://ai-release.org/"
    }
  ],
  "claims": [
    {
      "id": "AR-RYZEN98940-001",
      "statement": "A MAIBENBEN X17F laptop with a Ryzen 9 8940HX and a GeForce RTX 5060 Laptop GPU ran four coder models, including Qwen3-Coder-30B-A3B and DeepSeek-Coder-V2-Lite.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-001",
      "evidence_excerpt": "A MAIBENBEN X17F laptop with a Ryzen 9 8940HX and a GeForce RTX 5060 Laptop GPU ran four coder models, including Qwen3-Coder-30B-A3B and DeepSeek-Coder-V2-Lite."
    },
    {
      "id": "AR-RYZEN98940-002",
      "statement": "Only 29% to 38% of the weights fit in 8 GB of VRAM ; the engine offloads the rest to system RAM, and the tests ran on 40 GB of RAM.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-002",
      "evidence_excerpt": "Only 29% to 38% of the weights fit in 8 GB of VRAM ; the engine offloads the rest to system RAM, and the tests ran on 40 GB of RAM."
    },
    {
      "id": "AR-RYZEN98940-003",
      "statement": "VRAM isn't the only bottleneck: two shards of Qwen3.8-Flash-Next Coder were partially read straight off the SSD.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-003",
      "evidence_excerpt": "VRAM isn't the only bottleneck: two shards of Qwen3.8-Flash-Next Coder were partially read straight off the SSD."
    },
    {
      "id": "AR-RYZEN98940-004",
      "statement": "An author going by Lexus08 took a MAIBENBEN X17F gaming laptop — AMD Ryzen 9 8940HX, NVIDIA GeForce RTX 5060 Laptop with 8 GB of GDDR7, a single 24 GB DDR5 module, a 17.3-inch display — and turned it into a local AI workstation: the article on Habr .",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-004",
      "evidence_excerpt": "An author going by Lexus08 took a MAIBENBEN X17F gaming laptop — AMD Ryzen 9 8940HX, NVIDIA GeForce RTX 5060 Laptop with 8 GB of GDDR7, a single 24 GB DDR5 module, a 17.3-inch display — and turned it into a local AI workstation: the article on Habr ."
    },
    {
      "id": "AR-RYZEN98940-005",
      "statement": "A second 24 GB module brought the total to 48 GB, but the measurements were taken at 40 GB to keep the engine comparison fair.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-005",
      "evidence_excerpt": "A second 24 GB module brought the total to 48 GB, but the measurements were taken at 40 GB to keep the engine comparison fair."
    },
    {
      "id": "AR-RYZEN98940-006",
      "statement": "The laptop was kept in performance mode — via a dedicated key or the profiles app — otherwise the system falls back to the integrated GPU.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-006",
      "evidence_excerpt": "The laptop was kept in performance mode — via a dedicated key or the profiles app — otherwise the system falls back to the integrated GPU."
    },
    {
      "id": "AR-RYZEN98940-007",
      "statement": "The mechanics are described layer by layer.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-007",
      "evidence_excerpt": "The mechanics are described layer by layer."
    },
    {
      "id": "AR-RYZEN98940-008",
      "statement": "\"Hot\" weights and the KV cache go into VRAM, while the rest lives in system RAM and gets computed on the CPU.",
      "claim_type": "reported_fact",
      "confidence": "not_assessed",
      "source_type": "publication source",
      "verification_status": "reported_unverified",
      "source_url": "https://habr.com/ru/articles/1105358/",
      "article_anchor": "#ai-claim-008",
      "evidence_excerpt": "\"Hot\" weights and the KV cache go into VRAM, while the rest lives in system RAM and gets computed on the CPU."
    }
  ],
  "relationships": [
    {
      "subject": "habr.com",
      "predicate": "reports on",
      "object": "Ryzen 9 8940HX and RTX 5060: Running Local LLMs on a Laptop with 8 GB of VRAM",
      "claim_id": "AR-RYZEN98940-001"
    },
    {
      "subject": "AI Release",
      "predicate": "publishes",
      "object": "Ryzen 9 8940HX and RTX 5060: Running Local LLMs on a Laptop with 8 GB of VRAM",
      "claim_id": "AR-RYZEN98940-001"
    }
  ],
  "questions_and_answers": [
    {
      "question": "What is this article about?",
      "answer": "Ryzen 9 8940HX and RTX 5060: Running Local LLMs on a Laptop with 8 GB of VRAM. A MAIBENBEN X17F laptop with a Ryzen 9 8940HX and a GeForce RTX 5060 Laptop GPU ran four coder models, including Qwen3-Coder-30B-A3B and DeepSeek-Coder-V2-Lite.",
      "claim_ids": [
        "AR-RYZEN98940-001"
      ],
      "article_anchor": "#ai-knowledge"
    },
    {
      "question": "What happened?",
      "answer": "A MAIBENBEN X17F laptop with a Ryzen 9 8940HX and a GeForce RTX 5060 Laptop GPU ran four coder models, including Qwen3-Coder-30B-A3B and DeepSeek-Coder-V2-Lite. Only 29% to 38% of the weights fit in 8 GB of VRAM ; the engine offloads the rest to system RAM, and the tests ran on 40 GB of RAM. VRAM isn't the only bottleneck: two shards of Qwen3.8-Flash-Next Coder were partially read straight off the SSD.",
      "claim_ids": [
        "AR-RYZEN98940-001",
        "AR-RYZEN98940-002",
        "AR-RYZEN98940-003"
      ],
      "article_anchor": "#ai-knowledge"
    },
    {
      "question": "Who is the source?",
      "answer": "habr.com: https://habr.com/ru/articles/1105358/",
      "claim_ids": [],
      "article_anchor": "#ai-knowledge"
    },
    {
      "question": "What remains unknown?",
      "answer": "The article reports the cited source; independent verification and full details are not provided.",
      "claim_ids": [],
      "article_anchor": "#ai-knowledge"
    }
  ],
  "limitations": [
    "No independent verification is provided.",
    "Full details, dates and official documents may be missing.",
    "The article reports a source rather than being the primary source."
  ],
  "citation": {
    "preferred_citation": "AI Release. «Ryzen 9 8940HX and RTX 5060: Running Local LLMs on a Laptop with 8 GB of VRAM». 2026-11-17. https://ai-release.org/posts/ryzen-9-8940hx-i-rtx-5060-lokalnye-llm-na-noutbuke-s-8-gb-vram-e0ee9858_en.html",
    "canonical_url": "https://ai-release.org/posts/ryzen-9-8940hx-i-rtx-5060-lokalnye-llm-na-noutbuke-s-8-gb-vram-e0ee9858_en.html",
    "publisher": "AI Release"
  }
}