llamafile ripper

AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Pop 22.04 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 2401191-NE-LLAMAFILE37
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

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
January 19
  13 Minutes
b
January 19
  11 Minutes
c
January 19
  12 Minutes
d
January 19
  13 Minutes
Invert Hiding All Results Option
  12 Minutes

Only show results where is faster than
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):


llamafile ripperOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS)AMD Starship/Matisse4 x 32 GB DRAM-3000MT/s CMK64GX4M2D3000C16Samsung SSD 970 EVO Plus 500GBAMD Radeon RX 5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Pop 22.046.6.6-76060606-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.44.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54)1.3.267GCC 11.4.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionLlamafile Ripper BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107a- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%101%101%102%102%LlamafileLlamafileLlamafilellava-v1.5-7b-q4 - CPUmistral-7b-instruct-v0.2.Q8_0 - CPUwizardcoder-python-34b-v1.0.Q6_K - CPU

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 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabcd3691215SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 311.8111.6411.5711.57
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabcd3691215Min: 11.75 / Avg: 11.81 / Max: 11.9Min: 11.6 / Avg: 11.64 / Max: 11.7Min: 11.54 / Avg: 11.57 / Max: 11.59Min: 11.55 / Avg: 11.57 / Max: 11.59

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUabcd246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.657.717.687.65
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUabcd3691215Min: 7.62 / Avg: 7.65 / Max: 7.67Min: 7.7 / Avg: 7.71 / Max: 7.72Min: 7.67 / Avg: 7.68 / Max: 7.7Min: 7.64 / Avg: 7.65 / Max: 7.68

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabcd0.54231.08461.62692.16922.7115SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.412.402.412.40
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabcd246810Min: 2.41 / Avg: 2.41 / Max: 2.41Min: 2.4 / Avg: 2.4 / Max: 2.41Min: 2.4 / Avg: 2.41 / Max: 2.41Min: 2.4 / Avg: 2.4 / Max: 2.41