{
  "listings": [
    {
      "slug": "hyperqwen",
      "name": "HyperQwen",
      "company": "syv.ai (Copenhagen, CVR DK44671247)",
      "grade": "C",
      "fit": "yes",
      "why": "CTX=long gives 150k and CTX=huge 240k with measured decode rates and cold time-to-first-token at 66k and 100k. vLLM sizes the KV pool at start and the README states the pool size per arm.",
      "source": "https://github.com/syv-ai/HyperQwen/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/hyperqwen"
    },
    {
      "slug": "docker-model-runner",
      "name": "Docker Model Runner",
      "company": "Docker, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Context is configured per model, but the account shows the stored value not always applied at load, with the packaged 128k default used instead.",
      "source": "https://github.com/docker/model-runner/issues/1025",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/docker-model-runner"
    },
    {
      "slug": "jan",
      "name": "Jan",
      "company": "Menlo Research Pte Ltd",
      "grade": "C",
      "fit": "caveat",
      "why": "Context size is a per-model setting and Fit to Hardware caps it where enabled. Nothing documents the default, what happens past it, or an API field reporting the active value.",
      "source": "https://github.com/janhq/jan/blob/main/docs/src/pages/docs/desktop/model-parameters.mdx",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/jan"
    },
    {
      "slug": "koboldcpp",
      "name": "KoboldCpp",
      "company": "LostRuins (Concedo)",
      "grade": "B",
      "fit": "caveat",
      "why": "--contextsize sets the window and /api/extra/true_max_context_length reports it over the API. Smart Context and context shift drop the oldest half when full rather than rejecting, so long sessions lose their prefix silently.",
      "source": "https://github.com/LostRuins/koboldcpp/wiki",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/koboldcpp"
    },
    {
      "slug": "lemonade",
      "name": "Lemonade",
      "company": "Advanced Micro Devices, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "ctx_size is set per load and /v1/models reports the active context_length. The Strix Halo issue shows a compute crash past 33k while 262k was advertised, with no maintainer reply when read.",
      "source": "https://github.com/lemonade-sdk/lemonade/blob/main/docs/api/lemonade.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lemonade"
    },
    {
      "slug": "llama-cpp",
      "name": "llama.cpp",
      "company": "ggml.ai, part of Hugging Face since 2026",
      "grade": "D",
      "fit": "caveat",
      "why": "--ctx-size defaults to the model's trained length, /props and /slots expose n_ctx, responses carry a truncated flag. One account got 128k on 16 GB; another hit a tool loop past 30k until a parser fix.",
      "source": "https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/llama-cpp"
    },
    {
      "slug": "mlx-lm",
      "name": "MLX LM",
      "company": "Apple Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "A rotating fixed-size KV cache keeps generation going by discarding older tokens, which is silent truncation of the prefix; the quantised cache disables batching. No API field reports the active context.",
      "source": "https://github.com/ml-explore/mlx-lm/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mlx-lm"
    },
    {
      "slug": "ollama",
      "name": "Ollama",
      "company": "Ollama Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "OLLAMA_CONTEXT_LENGTH or num_ctx sets 64k and ollama ps shows the allocated context. The default is 4k below 24 GiB and prompts past it are truncated with no error, per two accounts.",
      "source": "https://docs.ollama.com/context-length",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/ollama"
    },
    {
      "slug": "privategpt",
      "name": "PrivateGPT",
      "company": "PriBAI Technology Spain S.L.",
      "grade": "C",
      "fit": "caveat",
      "why": "context_window must be set explicitly in the model profile to avoid overflow; the backend decides the rest.",
      "source": "https://docs.privategpt.dev/configuration/advanced",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/privategpt"
    },
    {
      "slug": "text-generation-webui",
      "name": "TextGen",
      "company": "oobabooga",
      "grade": "E",
      "fit": "caveat",
      "why": "ctx_size is set per load (32768 in the example) and --parallel N gives llama.cpp slots. No field reports the active context and nothing says whether over-length prompts are rejected.",
      "source": "https://github.com/oobabooga/textgen/blob/main/docs/12%20-%20OpenAI%20API.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/text-generation-webui"
    },
    {
      "slug": "vllm",
      "name": "vLLM",
      "company": "The Linux Foundation (vLLM is a PyTorch Foundation project)",
      "grade": "D",
      "fit": "caveat",
      "why": "--max-model-len fixes the window and the KV pool is sized at start, with a Context Extension feature page. Whether an over-length request is rejected or truncated was not read.",
      "source": "https://docs.vllm.ai/en/stable/serving/online_serving/openai_compatible_server/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vllm"
    },
    {
      "slug": "foundry-local",
      "name": "Foundry Local",
      "company": "Microsoft Corporation",
      "grade": "B",
      "fit": "unchecked",
      "why": "No context length setting or report appears in the REST, CLI or SDK reference pages read.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/foundry-local"
    },
    {
      "slug": "ghost-core",
      "name": "Core",
      "company": "ZMJ, Inc., doing business as Ghost, 325 9th Street, San Francisco, CA 94103, United States",
      "grade": "F",
      "fit": "unchecked",
      "why": "No context lengths are stated for any listed model.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/ghost-core"
    },
    {
      "slug": "gpt4all",
      "name": "GPT4All",
      "company": "Nomic, Inc.",
      "grade": "F",
      "fit": "unchecked",
      "why": "Context Length is a setting, but the docs state no default, no behaviour past it and no API field for the active value.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/gpt4all"
    },
    {
      "slug": "lm-studio",
      "name": "LM Studio",
      "company": "Element Labs, Inc.",
      "grade": "C",
      "fit": "unchecked",
      "why": "The context length page (/docs/app/advanced/context-length) returns 404 and the developer docs read do not state the default or whether the API reports the active value.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lm-studio"
    },
    {
      "slug": "localai",
      "name": "LocalAI",
      "company": "Ettore Di Giacinto and the LocalAI team",
      "grade": "B",
      "fit": "unchecked",
      "why": "Per-model context size configuration and its default were not found in the pages read.",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/localai"
    },
    {
      "slug": "underdog",
      "name": "Underdog",
      "company": "Conway Research",
      "grade": "F",
      "fit": "unchecked",
      "why": "No context length is stated on the card.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/underdog"
    },
    {
      "slug": "anythingllm",
      "name": "AnythingLLM",
      "company": "Mintplex Labs, Inc.",
      "grade": "E",
      "fit": "no",
      "why": "Context length belongs to the configured LLM provider.",
      "source": "https://docs.anythingllm.com/features/api",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/anythingllm"
    },
    {
      "slug": "berth",
      "name": "Berth",
      "company": "Trevin Tindall (T-Crypt on GitHub)",
      "grade": "B",
      "fit": "no",
      "why": "Context belongs to the engine; Berth only saves and restores its KV slots across switches.",
      "source": "https://github.com/T-Crypt/berth/blob/main/docs/gateway.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/berth"
    },
    {
      "slug": "bitrun",
      "name": "BitRun",
      "company": "Abhishek Khanra (IshekKhal on GitHub)",
      "grade": "E",
      "fit": "no",
      "why": "The largest catalogue context is 8,192 tokens.",
      "source": "https://github.com/IshekKhal/bitrun/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bitrun"
    },
    {
      "slug": "khoj",
      "name": "Khoj",
      "company": "Khoj Inc.",
      "grade": "E",
      "fit": "no",
      "why": "Context handling belongs to the configured model server.",
      "source": "https://docs.khoj.dev/get-started/setup",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/khoj"
    },
    {
      "slug": "localghost",
      "name": "LocalGhost",
      "company": "LocalGhost.ai Ltd (company number 17213100, registered in England and Wales, incorporated 12 May 2026)",
      "grade": "F",
      "fit": "no",
      "why": "No agent sessions.",
      "source": "https://github.com/LocalGhostDao/localghost/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/localghost"
    },
    {
      "slug": "open-webui",
      "name": "Open WebUI",
      "company": "Open WebUI Inc.",
      "grade": "D",
      "fit": "no",
      "why": "Context length belongs to the connected backend; the interface sets none of its own.",
      "source": "https://docs.openwebui.com/reference/api-endpoints",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/open-webui"
    },
    {
      "slug": "screenpipe",
      "name": "screenpipe",
      "company": "Negentropy Labs, Inc. (dba Screenpipe)",
      "grade": "C",
      "fit": "no",
      "why": "Not a model server.",
      "source": "https://docs.screenpipe.com/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/screenpipe"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 8,
    "after": [
      "local-ai.coding-agent-backend"
    ],
    "area": "models",
    "asks": [
      "set the context to 64k for Claude Code",
      "why did the model forget the start of the task",
      "run a 100k token repository read locally",
      "stop the model looping once the conversation is long"
    ],
    "before": [
      "local-ai.fit-model-to-hardware"
    ],
    "blockers": [
      "default context of 2k or 4k with prompts silently truncated rather than rejected",
      "hardware backend crashes with a compute error past about 33k tokens while advertising 262k",
      "model repeats the same tool call once the context is long"
    ],
    "capabilities": [
      "inference.local",
      "inference.context-64k"
    ],
    "category": "local-ai",
    "categoryName": "Local AI",
    "checked": "2026-11-12",
    "companies": {
      "fit": 1,
      "fitWithLimit": 10,
      "tagged": 26
    },
    "competition": "one",
    "fits": [
      "hyperqwen"
    ],
    "fitsWithLimit": [
      "docker-model-runner",
      "jan",
      "koboldcpp",
      "lemonade",
      "llama-cpp",
      "mlx-lm",
      "ollama",
      "privategpt",
      "text-generation-webui",
      "vllm"
    ],
    "id": "local-ai.long-context-agent-session",
    "listings": {
      "caveat": 10,
      "no": 7,
      "notRead": 0,
      "tagged": 26,
      "unchecked": 6,
      "yes": 1
    },
    "name": "Keep a 32k to 128k token agent session without silent truncation or a crash",
    "status": "draft",
    "success": "A 60k token prompt is accepted whole and the server reports the active context length through its API. Measured: the response shows no sign of a truncated prefix, and the same tool works at 60k as at 5k.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/local-ai.long-context-agent-session.json",
    "weight": 8,
    "weightBasis": "8 of 50 accounts hit a context limit: the 2k or 4k default, a crash past 33k, or tool loops past 30k"
  }
}
