xeon max llamafile

2 x Intel Xeon Max 9480 testing with a Supermicro SYS-221H-TNR X13DEM v1.10 (1.3 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2404031-NE-XEONMAXLL89
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
April 04
  18 Minutes
b
April 04
  7 Minutes
Invert Hiding All Results Option
  12 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


xeon max llamafileOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads)Supermicro SYS-221H-TNR X13DEM v1.10 (1.3 BIOS)Intel Device 1bce512GB7682GB INTEL SSDPF2KX076TZASPEED2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200GbUbuntu 23.106.9.0-060900rc2-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7GCC 13.2.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionXeon Max Llamafile BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c000290- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Llamafile

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.7Test: llava-v1.5-7b-q4 - Acceleration: CPUab0.5221.0441.5662.0882.611.512.32

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.7Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUab0.83251.6652.49753.334.16253.663.70

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.7Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUa0.13280.26560.39840.53120.6640.59