llama

AMD Ryzen 7 9800X3D 8-Core testing with a ASRock X870E Taichi (3.12.AS02 BIOS) and AMD Radeon PRO W7500 8GB on Ubuntu 24.04 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 2412052-PTS-LLAMA11353
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
Allow Limiting Results To Certain Suite(s)

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
Disable Color Branding
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 05
  1 Hour, 49 Minutes
b
December 05
  35 Minutes
AMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB
December 05
  35 Minutes
c
December 05
  35 Minutes
Invert Behavior (Only Show Selected Data)
  53 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):


llamaOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 9800X3D 8-Core @ 6.22GHz (8 Cores / 16 Threads)ASRock X870E Taichi (3.12.AS02 BIOS)AMD Device 14d82 x 16GB DDR5-6000MT/s F5-6000J2836G16GWestern Digital WD_BLACK SN850X 2000GBAMD Radeon PRO W7500 8GBAMD Navi 31 HDMI/DPDELL U2723QERealtek Device 8126 + MEDIATEK Device 0717Ubuntu 24.046.8.0-49-generic (x86_64)GNOME Shell 46.0X Server 1.21.1.11 + Wayland4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.58)GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionLlama BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xb404023 - 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GBcResult OverviewPhoronix Test Suite100%102%103%105%107%LlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafileLlamafilewizardcoder-python-34b-v1.0.Q6_K - Text Generation 16TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 16Llama-3.2-3B-Instruct.Q6_K - Text Generation 16mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 16TinyLlama-1.1B-Chat-v1.0.BF16 - T.G.1mistral-7b-instruct-v0.2.Q5_K_M - T.G.1Llama-3.2-3B-Instruct.Q6_K - T.G.1wizardcoder-python-34b-v1.0.Q6_K - P.P.2wizardcoder-python-34b-v1.0.Q6_K - T.G.1mistral-7b-instruct-v0.2.Q5_K_M - P.P.2wizardcoder-python-34b-v1.0.Q6_K - P.P.1mistral-7b-instruct-v0.2.Q5_K_M - P.P.1Llama-3.2-3B-Instruct.Q6_K - P.P.2wizardcoder-python-34b-v1.0.Q6_K - P.P.5mistral-7b-instruct-v0.2.Q5_K_M - P.P.5wizardcoder-python-34b-v1.0.Q6_K - P.P.2Llama-3.2-3B-Instruct.Q6_K - P.P.1TinyLlama-1.1B-Chat-v1.0.BF16 - P.P.2mistral-7b-instruct-v0.2.Q5_K_M - P.P.2Llama-3.2-3B-Instruct.Q6_K - P.P.5TinyLlama-1.1B-Chat-v1.0.BF16 - P.P.1Llama-3.2-3B-Instruct.Q6_K - P.P.2TinyLlama-1.1B-Chat-v1.0.BF16 - P.P.5TinyLlama-1.1B-Chat-v1.0.BF16 - P.P.2

llamallamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 2048llamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 128llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 2048llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 1024llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 128llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 1024llamafile: wizardcoder-python-34b-v1.0.Q6_K - Text Generation 16llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 2048llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 512llamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 128llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 128llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 512llamafile: wizardcoder-python-34b-v1.0.Q6_K - Prompt Processing 256llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 1024llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 2048llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Prompt Processing 256llamafile: mistral-7b-instruct-v0.2.Q5_K_M - Text Generation 16llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 512llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 1024llamafile: Llama-3.2-3B-Instruct.Q6_K - Text Generation 16llamafile: Llama-3.2-3B-Instruct.Q6_K - Prompt Processing 256llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Text Generation 16llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 512llamafile: TinyLlama-1.1B-Chat-v1.0.BF16 - Prompt Processing 256abAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GBc122882.132768614411.31163842.0932768307221.4227.57819215361638432768409611.1981921638421.47409627.5481924096122882.132768614411.316384232768307221.4227.51819215361638432768409610.9481921638420.78409626.2881924096122882.132768614411.3163841.9832768307221.4327.55819215361638432768409610.9481921638420.77409626.4281924096122882.132768614411.3163841.9632768307221.4327.52819215361638432768409610.9581921638420.79409626.5181924096OpenBenchmarking.org

Llamafile

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 2048cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB3K6K9K12K15KSE +/- 0.00, N = 312288122881228812288

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 128cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB0.47250.9451.41751.892.3625SE +/- 0.00, N = 32.12.12.12.1

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 2048cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB7K14K21K28K35KSE +/- 0.00, N = 332768327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 1024cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB13002600390052006500SE +/- 0.00, N = 36144614461446144

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 128cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB3691215SE +/- 0.00, N = 311.3011.3011.3111.30

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 1024cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB4K8K12K16K20KSE +/- 0.00, N = 316384163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Text Generation 16cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB0.47030.94061.41091.88122.3515SE +/- 0.02, N = 121.962.002.091.98

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 2048cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB7K14K21K28K35KSE +/- 0.00, N = 332768327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 512cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB7001400210028003500SE +/- 0.00, N = 33072307230723072

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 128cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB510152025SE +/- 0.00, N = 321.4321.4221.4221.43

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 128cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB612182430SE +/- 0.02, N = 327.5227.5127.5727.55

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 512cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB2K4K6K8K10KSE +/- 0.00, N = 38192819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: wizardcoder-python-34b-v1.0.Q6_K - Test: Prompt Processing 256cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB30060090012001500SE +/- 0.00, N = 31536153615361536

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 1024cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB4K8K12K16K20KSE +/- 0.00, N = 316384163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 2048cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB7K14K21K28K35KSE +/- 0.00, N = 332768327683276832768

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Prompt Processing 256cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB9001800270036004500SE +/- 0.00, N = 34096409640964096

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: mistral-7b-instruct-v0.2.Q5_K_M - Test: Text Generation 16cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB3691215SE +/- 0.13, N = 310.9510.9411.1910.94

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 512cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB2K4K6K8K10KSE +/- 0.00, N = 38192819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 1024cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB4K8K12K16K20KSE +/- 0.00, N = 316384163841638416384

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Text Generation 16cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB510152025SE +/- 0.01, N = 320.7920.7821.4720.77

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: Llama-3.2-3B-Instruct.Q6_K - Test: Prompt Processing 256cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB9001800270036004500SE +/- 0.00, N = 34096409640964096

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Text Generation 16cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB612182430SE +/- 0.00, N = 326.5126.2827.5426.42

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 512cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB2K4K6K8K10KSE +/- 0.00, N = 38192819281928192

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.8.16Model: TinyLlama-1.1B-Chat-v1.0.BF16 - Test: Prompt Processing 256cbaAMD Ryzen 7 9800X3D 8-Core - AMD Radeon PRO W7500 8GB9001800270036004500SE +/- 0.00, N = 34096409640964096