Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Meta

Meta-Llama-3.1-8B-Instruct

Benchmark profile and published results.

Dense8B
Position in the field

Bestwerte im Vergleich

Best metrics of this model against the minimum, average and maximum of all published systems.

Generation83,4 tok/s
Min 0,0Ø 244,1Max 1.443,9
Unter dem Durchschnitt · 596 Systeme im Feld
Prefill2.658 tok/s
Min 6Ø 5.354Max 39.029
Unter dem Durchschnitt · 595 Systeme im Feld
Time to First Token1.773 ms
Min 91Ø 13.148Max 299.591
Ueber dem Durchschnitt · 597 Systeme im Feld
Performance profile

Throughput by hardware & engine

Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.

GPUnach Grafikkarte

10880,853,826,90,008031.6072.410Prefill (tok/s)Generation (tok/s)AMD Radeon 8060S Graphics - 83,4 tok/s Generation, 1.949 tok/s Prefill, TTFT 6.369 ms (3 Laufe)AMD Radeon 8060S Grap...CPU-only - 3,6 tok/s Generation, 36 tok/s Prefill, TTFT 59.044 ms (1 Lauf)CPU-only
AMD Radeon 8060S Graphics 83,4 tok/sCPU-only 3,6 tok/s

CPUnach Prozessor

10880,853,826,90,008031.6072.410Prefill (tok/s)Generation (tok/s)AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 83,4 tok/s Generation, 1.949 tok/s Prefill, TTFT 6.369 ms (3 Laufe)AMD RYZEN AI MAX+ 395...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 3,6 tok/s Generation, 36 tok/s Prefill, TTFT 59.044 ms (1 Lauf)Intel(R) Xeon(R) CPU ...
AMD RYZEN AI MAX+ 395 w/ Radeon 8060S 83,4 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 3,6 tok/s

ENGnach Engine

91,787,583,479,275,01.3821.4411.5001.559Prefill (tok/s)Generation (tok/s)llama.cpp - 83,4 tok/s Generation, 1.471 tok/s Prefill, TTFT 19.538 ms (4 Laufe)llama.cpp
llama.cpp 83,4 tok/s
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.
Throughput & latency

Performance benchmark

Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Meta-Llama-3.1-8B-InstructMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
83,37 tok/s TG
Prefill 2.658 · TTFT 10.905 ms
10×AMD Radeon 8060S Graphics32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_K_MDetails →
2Meta-Llama-3.1-8B-InstructMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
76,24 tok/s TG
Prefill 1.951 · TTFT 6.429 ms
5×AMD Radeon 8060S Graphics32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_K_MDetails →
3Meta-Llama-3.1-8B-InstructMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
40,39 tok/s TG
Prefill 1.237 · TTFT 1.773 ms
1×AMD Radeon 8060S Graphics32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMllama.cppgodclawQ4_K_MDetails →
4Meta-Llama-3.1-8B-InstructMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,55 tok/s TG
Prefill 36 · TTFT 59.044 ms
1×Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →