[
  {
    "id": "llamafile-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile",
    "excerpt": "llamafile lets you distribute and run LLMs with a single file.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-2",
    "tier": "claimed-docs",
    "url": "https://www.mozilla.ai/open-tools/llamafile",
    "excerpt": "Models run entirely on your device. No cloud, no data sharing, no external dependencies. Works fully offline for privacy-first AI workflows.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/getting-started/pre-built-llamafiles",
    "excerpt": "We provide pre-built llamafiles for a variety of models, so you can easily run them immediately without setup.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/getting-started/quickstart",
    "excerpt": "you can also upload an image by using the `/upload` command and specifying the path to the image",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/getting-started/quickstart",
    "excerpt": "you can also chat with it using [llama.cpp](https://github.com/ggml-org/llama.cpp)'s Web UI: just open a browser window and connect to http://localhost:8080/",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/using-llamafile/running_llamafile",
    "excerpt": "If you add the `--cli` argument to a llamafile, you will run a CLI version of the model that answers to whatever you provide as a prompt",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/using-llamafile/running_llamafile",
    "excerpt": "Here's how you can use llamafile to describe a jpg/png/gif/bmp image with a multimodal model (Qwen3.5, Ministral3, llava1.6 are all good candidates)",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/using-llamafile/creating_llamafiles",
    "excerpt": "A llamafile bundles the llamafile executable, model weights, and a set of default arguments into a single self-contained file using the APE (Actually Portable Executable) format",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/reference/cli_arguments",
    "excerpt": "llamafile --server --help ... HTTP server, API, Web UI, slot, and server sandbox options.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/reference/security",
    "excerpt": "No outbound network. `anet` allows `accept()` but not `connect()`, so the only networking the server can do is answer connections it received.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-11",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/reference/support",
    "excerpt": "llamafile supports the following operating systems, which require a minimum stock install",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-docs-12",
    "tier": "claimed-docs",
    "url": "https://docs.mozilla.ai/llamafile/reference/support",
    "excerpt": "llamafile ships GPU acceleration for Apple Metal, NVIDIA, AMD, and Vulkan.",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-gh-1",
    "tier": "github",
    "url": "https://github.com/mozilla-ai/llamafile",
    "excerpt": "llamafile also includes whisperfile, a single-file speech-to-text tool built on whisper.cpp and the same Cosmopolitan packaging. It supports transcription and translation of audio files",
    "fetchedAt": "2026-09-04T21:02:18.630Z"
  },
  {
    "id": "llamafile-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "Author here. llamafile will work on stock Windows installs using CPU inference. No CUDA or MSVC or DLLs are required! The dev tools are only required to be installed, right now, if you want get faster GPU performance.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-2",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "My attempt to run it with VS 2022 dev console and newly downloaded CUDA installation ended in flames as compilation stopped with 'error limit reached', followed by it defaulting to a CPU run. It does run on the CPU though, so at least that's pretty cool.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-3",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "The CPU usage is around 30% when idle (not handling any HTTP requests) under Windows, so you won't want to keep this app running in background. Otherwise, it's a nice try.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-4",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "So if you share a binary with a friend you'd have to have them install cuda toolkit too? Seems like a dealbreaker for the whole idea.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-5",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "This is pretty darn crazy. One file runs on 6 operating systems, with GPU support.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-6",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "great! worked easily on desktop Linux, first try. It appears to execute with zero network connection... thx to Mozilla and Justin Tunney for this very easy, local experiment today!",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-7",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "Why is this faster than running llama.cpp main directly? I'm getting 7 tokens/sec with this. But 2 with llama.cpp by itself",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-8",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "Can confirm that this runs on an ancient i3 NUC under Ubuntu 20.04. It emits a token every five or six seconds, which is 'ask a question then go get coffee' speed. Still, very cool.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-9",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "I get the desire to make self-contained things, but a binary that only runs one model with one set of weights seems awfully constricting to me.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-10",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38464057",
    "excerpt": "But for anyone in a production/business setting, it would be tough to see this being viable. Seems like it would be a non-starter for most medium to large companies IT teams. The great thing about a Dockerfile is that it can be inspected.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-11",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38489533",
    "excerpt": "It's not the best way. It's a really cool and technically interesting way. But embedding the model with the executable is terrible for anything beyond a demo... it's far from best for people that actually want to explore LLM and play.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-12",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38489533",
    "excerpt": "Doesn't work on my NixOS workstation.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-13",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/38489533",
    "excerpt": "I've tried running Llamafile on my Lenovo Legion Pro 5 laptop with 8GB VRAM, but it has a dashboard that shows the GPU and CPU utilisation in real time, and almost all the processing is done on the CPU. Is there a way to shift the processing to the GPU?",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-14",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39887263",
    "excerpt": "I have tried out Llamafile and I think it is bloody great. The simplicity of it is commendable. One issue I hope they overcome for Windows however, is being able to run the executable when it's more than 4GB (a Windows limitation).",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-15",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39887263",
    "excerpt": "I use my llamafile nearly every day.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-16",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=40380158",
    "excerpt": "I'd be really impressed with Mozilla if they could do the entire thing (llamafile + llamaindex) in one, or even two files. Having to set up a separate python install just for this task and pull in all the llamaindex python deps defeats the point of using llamafile.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-17",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/45753850",
    "excerpt": "Cosmocc and Cosmopolitan are remarkable technical achievements and llamafile made me discover them. The llamafile UX (CLI interface and web server with chat) is great... However I fail to see use cases where I would build a solution built on a llamafile.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-18",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/45753850",
    "excerpt": "there is anyway a nuance for Window systems which is the size limit for a Windows executable which is 4Gb maximum. As LLM models are tend to be quite large this limit is reached pretty fast.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-19",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/45753850",
    "excerpt": "It seems people have moved on from Llamafile. I doubt Mozilla AI is going to bring it back. This announcement didn't even come with a new code commit, just a wish.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-comm-20",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/45753850",
    "excerpt": "I'm glad to see llamafile being resurrected. A few things I hope for: 1. Curate a continuously extended inventory of prebuilt llamafiles 2. Create both flexible and slim minimalist builds 3. Upstreaming as much as they can into llama.cpp.",
    "fetchedAt": "2026-09-04T21:05:05.187Z"
  },
  {
    "id": "llamafile-probe-1",
    "tier": "probe",
    "url": "https://docs.mozilla.ai/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.mozilla.ai/llms.txt # Mozilla.ai Docs\n\n## any-llm\n\n- [Introduction](https://docs.mozilla.ai/index.md)\n- [Quickstart](https://docs.mozilla.ai",
    "fetchedAt": "2026-09-04T21:05:54.383Z"
  },
  {
    "id": "llamafile-probe-2",
    "tier": "probe",
    "url": "https://docs.mozilla.ai/llamafile.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://docs.mozilla.ai/llamafile.md # Page Not Found\n\nThe URL `llamafile` does not exist. This page may have been moved, renamed, or deleted.\n\n## Suggested",
    "fetchedAt": "2026-09-04T21:05:54.383Z"
  },
  {
    "id": "llamafile-probe-3",
    "tier": "probe",
    "url": "https://docs.mozilla.ai/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://docs.mozilla.ai/openapi.json, https://docs.mozilla.ai/swagger.json, https://docs.mozilla.ai/api/openapi.json, https://docs.mozilla.ai/.well-known/openapi.json)",
    "fetchedAt": "2026-09-04T21:05:54.383Z"
  },
  {
    "id": "llamafile-probe-4",
    "tier": "probe",
    "url": "https://docs.mozilla.ai/llamafile/reference/cli_arguments",
    "excerpt": "official CLI documented at https://docs.mozilla.ai/llamafile/reference/cli_arguments",
    "fetchedAt": "2026-09-04T21:05:54.383Z"
  }
]