Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
New release version: update version.h and docs (#952)
Davide Eynard6490e16f7a8f
diff --git a/README.md b/README.mdindex 5ce0fcf5..57ff701b 100644--- a/README.md+++ b/README.md@@ -24,7 +24,7 @@ locally on most operating systems and CPU archiectures, with no installation.llamafile also includes **[whisperfile](https://docs.mozilla.ai/llamafile/whisperfile)**, a single-file speech-to-text tool built on [whisper.cpp](https://github.com/ggerganov/whisper.cpp) and the same Cosmopolitan packaging. It supports transcription and translation of audio files across all the same platforms, with no installation required.-## v0.10.0+## v0.10.***llamafile versions starting from 0.10.0 use a new build system**, aimed at keeping our code more easilyaligned with the latest versions of llama.cpp. This means they support more recent models and functionalities,@@ -32,7 +32,7 @@ but at the same time they might be missing some ofthe features you were accustomed to (check out [this doc](README_0.10.0.md) for a high-level description of what has been done). If you likedthe "classic experience" more, you will always be able to access the previous versions from our[releases](https://github.com/mozilla-ai/llamafile/releases) page. Our pre-built llamafiles always-show which version of the server they have been bundled with ([0.9.* example](https://huggingface.co/mozilla-ai/llava-v1.5-7b-llamafile), [0.10.* example](https://huggingface.co/mozilla-ai/llamafile_0.10.0)), so you will always know+show which version of the server they have been bundled with ([0.9.* example](https://huggingface.co/mozilla-ai/llava-v1.5-7b-llamafile), [0.10.* example](https://huggingface.co/mozilla-ai/llamafile_0.10)), so you will always knowwhich version of the software you are downloading.@@ -47,7 +47,7 @@ Download and run your first llamafile in minutes:```sh# Download an example model (Qwen3.5 0.8B)-curl -LO https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile+curl -LO https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile# Make it executable (macOS/Linux/BSD)chmod +x Qwen3.5-0.8B-Q8_0.llamafilediff --git a/docs/example_llamafiles.md b/docs/example_llamafiles.mdindex eb088001..519e107b 100644--- a/docs/example_llamafiles.md+++ b/docs/example_llamafiles.md@@ -1,24 +1,24 @@We provide example llamafiles for a variety of models, so you can easily try out llamafilewith different kinds of LLMs. The following table lists llamafiles bundled with the latest-available version of the server (v0.10.0). The smaller the file is, the more easily it will+available version of the server (v0.10.*). The smaller the file is, the more easily it willrun on your computer, even if no GPU is present (as a reference, Qwen3.5 0.8B Q8 generatestext on a Raspberry Pi5 at ~8 tokens/sec).| Model | Size | License | llamafile || --- | --- | --- | --- |-| [Qwen3.5 0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) Q8_0 | 1.6 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-0.8B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile) |-| [Qwen3.5 2B](https://huggingface.co/Qwen/Qwen3.5-2B) Q8_0 | 3.2 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-2B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-2B-Q8_0.llamafile) |-| [Ministral 3 3B Instruct 2512](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) Q4_K_M | 3.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile) |-| [Qwen3.5 4B](https://huggingface.co/Qwen/Qwen3.5-4B) Q5_K_S | 4.1 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-4B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-4B-Q5_K_S.llamafile) |-| [llava v1.6 mistral 7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) Q4_K_M | 5.3 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [llava-v1.6-mistral-7b-Q4_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/llava-v1.6-mistral-7b-Q4_K_M.llamafile) |-| [Apertus 8B Instruct 2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509) | 5.9 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Apertus-8B-Instruct-2509.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Apertus-8B-Instruct-2509.llamafile) |-| [Qwen3.5 9B](https://huggingface.co/Qwen/Qwen3.5-9B) Q5_K_S | 7.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-9B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-9B-Q5_K_S.llamafile) |-| [Ministral 3 3B Instruct 2512](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) BF16 | 7.8 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Ministral-3-3B-Instruct-2512-BF16.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Ministral-3-3B-Instruct-2512-BF16.llamafile) |-| [llava v1.6 mistral 7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) Q8_0 | 8.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [llava-v1.6-mistral-7b-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/llava-v1.6-mistral-7b-Q8_0.llamafile) |-| [gpt-oss 20b](https://huggingface.co/openai/gpt-oss-20b) mxfp4 | 12 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [gpt-oss-20b-mxfp4.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/gpt-oss-20b-mxfp4.llamafile) |-| [gpt-oss 20b](https://huggingface.co/openai/gpt-oss-20b) Q5_K_S | 12 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [gpt-oss-20b-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/gpt-oss-20b-Q5_K_S.llamafile) |-| [LFM2 24B A2B](https://huggingface.co/LiquidAI/LFM2-24B-A2B) Q5_K_M | 16 GB | [lfm1.0](https://huggingface.co/LiquidAI/LFM2-24B-A2B/blob/main/LICENSE) | [LFM2-24B-A2B-Q5_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/LFM2-24B-A2B-Q5_K_M.llamafile) |-| [Qwen3.5 27B](https://huggingface.co/Qwen/Qwen3.5-27B) Q5_K_S | 19 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-27B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-27B-Q5_K_S.llamafile) |+| [Qwen3.5 0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) Q8_0 | 1.6 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-0.8B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile) |+| [Qwen3.5 2B](https://huggingface.co/Qwen/Qwen3.5-2B) Q8_0 | 3.2 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-2B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-2B-Q8_0.llamafile) |+| [Ministral 3 3B Instruct 2512](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) Q4_K_M | 3.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile) |+| [Qwen3.5 4B](https://huggingface.co/Qwen/Qwen3.5-4B) Q5_K_S | 4.1 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-4B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-4B-Q5_K_S.llamafile) |+| [llava v1.6 mistral 7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) Q4_K_M | 5.3 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [llava-v1.6-mistral-7b-Q4_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q4_K_M.llamafile) |+| [Apertus 8B Instruct 2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509) | 5.9 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Apertus-8B-Instruct-2509.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Apertus-8B-Instruct-2509.llamafile) |+| [Qwen3.5 9B](https://huggingface.co/Qwen/Qwen3.5-9B) Q5_K_S | 7.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-9B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-9B-Q5_K_S.llamafile) |+| [Ministral 3 3B Instruct 2512](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512) BF16 | 7.8 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Ministral-3-3B-Instruct-2512-BF16.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Ministral-3-3B-Instruct-2512-BF16.llamafile) |+| [llava v1.6 mistral 7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) Q8_0 | 8.4 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [llava-v1.6-mistral-7b-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q8_0.llamafile) |+| [gpt-oss 20b](https://huggingface.co/openai/gpt-oss-20b) mxfp4 | 12 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [gpt-oss-20b-mxfp4.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/gpt-oss-20b-mxfp4.llamafile) |+| [gpt-oss 20b](https://huggingface.co/openai/gpt-oss-20b) Q5_K_S | 12 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [gpt-oss-20b-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/gpt-oss-20b-Q5_K_S.llamafile) |+| [LFM2 24B A2B](https://huggingface.co/LiquidAI/LFM2-24B-A2B) Q5_K_M | 16 GB | [lfm1.0](https://huggingface.co/LiquidAI/LFM2-24B-A2B/blob/main/LICENSE) | [LFM2-24B-A2B-Q5_K_M.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/LFM2-24B-A2B-Q5_K_M.llamafile) |+| [Qwen3.5 27B](https://huggingface.co/Qwen/Qwen3.5-27B) Q5_K_S | 19 GB | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/) | [Qwen3.5-27B-Q5_K_S.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-27B-Q5_K_S.llamafile) |## Legacy llamafilesdiff --git a/docs/index.md b/docs/index.mdindex 95742376..8b514f7b 100644--- a/docs/index.md+++ b/docs/index.md@@ -24,7 +24,7 @@ locally on most operating systems and CPU archiectures, with no installation.llamafile also includes **[whisperfile](whisperfile/index.md)**, a single-file speech-to-text tool built on [whisper.cpp](https://github.com/ggerganov/whisper.cpp) and the same Cosmopolitan packaging. It supports transcription and translation of audio files across all the same platforms, with no installation required.-## v0.10.0+## v0.10.***llamafile versions starting from 0.10.0 use a new build system**, aimed at keeping our code more easilyaligned with the latest versions of llama.cpp. This means they support more recent models and functionalities,@@ -32,7 +32,7 @@ but at the same time they might be missing some ofthe features you were accustomed to (check out [this doc](https://github.com/mozilla-ai/llamafile/blob/main/README_0.10.0.md) for a high-level description of what has been done). If you likedthe "classic experience" more, you will always be able to access the previous versions from our[releases](https://github.com/mozilla-ai/llamafile/releases) page. Our pre-built llamafiles always-show which version of the server they have been bundled with ([0.9.* example](https://huggingface.co/mozilla-ai/llava-v1.5-7b-llamafile), [0.10.* example](https://huggingface.co/mozilla-ai/llamafile_0.10.0)), so you will always know+show which version of the server they have been bundled with ([0.9.* example](https://huggingface.co/mozilla-ai/llava-v1.5-7b-llamafile), [0.10.* example](https://huggingface.co/mozilla-ai/llamafile_0.10)), so you will always knowwhich version of the software you are downloading.diff --git a/docs/quickstart.md b/docs/quickstart.mdindex ae77dd88..f7e22654 100644--- a/docs/quickstart.md+++ b/docs/quickstart.md@@ -14,7 +14,7 @@ other hand, you have powerful hardware and/or GPUs, [feel free to choose](exampllarger and more expressive models which should provide more accurateresponses.-1. Download [Qwen3.5-0.8B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile) (1.77 GB).+1. Download [Qwen3.5-0.8B-Q8_0.llamafile](https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile) (1.77 GB).2. Open your computer's terminal.@@ -175,7 +175,7 @@ enable you to work around Windows' 4GB executable file size limit.For Windows users, here's an example for the gpt-oss LLM (whose size is >12GB):```sh-curl -L -o llamafile.exe https://huggingface.co/mozilla-ai/llamafile_0.10.0/resolve/main/llamafile_0.10.0+curl -L -o llamafile.exe https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llamafile_0.10.1curl -L -o gpt-oss.gguf https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-Q5_K_S.gguf./llamafile.exe -m gpt-oss.gguf```@@ -207,4 +207,4 @@ cd ~/.ollama/models/blobsllamafile -m sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29```**Note** that Ollama's GGUF weights do not always work with llama.cpp (see e.g. [here](https://forums.developer.nvidia.com/t/nemotron-3-super-120b-on-gb10-llama-cpp-sm-121-build-ollama-gguf-incompatibility-fix/363459)),-and as llamafile relies on llama.cpp this trick might not always work for you.\ No newline at end of file+and as llamafile relies on llama.cpp this trick might not always work for you.diff --git a/docs/support.md b/docs/support.mdindex 784fec2f..28fc4199 100644--- a/docs/support.md+++ b/docs/support.md@@ -81,6 +81,6 @@ In the event that GPU support couldn't be compiled and dynamicallylinked on the fly for any reason, llamafile will fall back to CPUinference.-**NOTE** that the 0.10.0 build of llamafile has not been tested on all+**NOTE** that the 0.10.* build of llamafile has not been tested on allGPUs/platforms yet, so we welcome your feedback both whether there are-any issues or if everything runs smoothly on your specific setup!\ No newline at end of file+any issues or if everything runs smoothly on your specific setup!diff --git a/llamafile/version.h b/llamafile/version.hindex 91429ea5..bfbf3c78 100644--- a/llamafile/version.h+++ b/llamafile/version.h@@ -20,7 +20,7 @@#define LLAMAFILE_MAJOR 0#define LLAMAFILE_MINOR 10-#define LLAMAFILE_PATCH 0+#define LLAMAFILE_PATCH 1#define LLAMAFILE_VERSION \(100000000 * LLAMAFILE_MAJOR + 1000000 * LLAMAFILE_MINOR + LLAMAFILE_PATCH)