Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options.
To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark llamafile.
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly. ** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform. Data updated weekly as of 25 December 2024.
Revision History
pts/llamafile-1.3.0 [View Source] Wed, 04 Dec 2024 12:43:19 GMT Update against llamafile 0.8.16.
pts/llamafile-1.2.0 [View Source] Sun, 02 Jun 2024 10:40:47 GMT Update against Llamafile 0.8.6 upstream.
Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16
OpenBenchmarking.org metrics for this test profile configuration based on 61 public results since 5 December 2024 with the latest data as of 20 December 2024.
Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.
Based on OpenBenchmarking.org data, the selected test / test configuration (Llamafile 0.8.16 - Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16) has an average run-time of 2 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.
Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.2%.
Tested CPU Architectures
This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.