Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🧠
Prozessor

4 x Cortex-A78C + 4 x Cortex-A55

Unbekannt
31Benchmarks
12Modelle
31Performance
0Harness
Beste Generation
19,6 tok/s
Qwen2.5-0.5B-Instruct
∅ Generation
5,5 tok/s
Schnitt aus 31 Läufen
Bester Prefill
171 tok/s
Prompt-Verarbeitung
Bester TTFT
29.146 ms
Time to First Token
Beste Harness-Quote
–%
noch kein Harness
🏆
Qwen2.5-0.5B-Instruct läuft am schnellsten auf dieser CPU · 19,6 tok/s
Bester Prefill: 171 tok/s · 12 Modelle getestet

Top-Modelle

Bester gemessener Durchsatz je Modell auf 4 x Cortex-A78C + 4 x Cortex-A55 – umschaltbar nach Generation, Prefill oder Kombiwert.

Qwen2.5-0.5B-Instruct
19,6 tok/s
Llama-3.2-1B-Instruct1B
13,2 tok/s
Qwen2.5-1.5B-Instruct
9,1 tok/s
Qwen3-0.6B0.6B
8,0 tok/s
gemma-2-2b-it2B
7,9 tok/s
Qwen3-1.7B1.7B
4,0 tok/s
Qwen2.5-3B-Instruct3B
3,5 tok/s
SmolLM2-1.7B-Instruct1.7B
3,1 tok/s
Llama-3.2-3B-Instruct3B
2,5 tok/s
Qwen3-8B8.2B
1,6 tok/s
Performanceprofil

Durchsatz auf 4 x Cortex-A78C + 4 x Cortex-A55

Jede Blase steht für ein Modell, eine Engine bzw. eine GPU – Position: Prompt-Verarbeitung (X) × Ausgabe (Y), Blasengröße: Anzahl Messläufe.

MODnach Modell

25,419,012,76,30,0053107160Prefill (tok/s)Generation (tok/s)Qwen2.5-0.5B-Instruct - 19,6 tok/s Generation, 130 tok/s Prefill, TTFT 103.850 ms (3 Laufe)Qwen2.5-0.5B-InstructLlama-3.2-1B-Instruct - 13,2 tok/s Generation, 94 tok/s Prefill, TTFT 134.150 ms (3 Laufe)Llama-3.2-1B-InstructQwen2.5-1.5B-Instruct - 9,1 tok/s Generation, 68 tok/s Prefill, TTFT 183.014 ms (3 Laufe)Qwen2.5-1.5B-InstructQwen3-0.6B - 8,0 tok/s Generation, 90 tok/s Prefill, TTFT 132.604 ms (3 Laufe)Qwen3-0.6Bgemma-2-2b-it - 7,9 tok/s Generation, 40 tok/s Prefill, TTFT 249.190 ms (3 Laufe)gemma-2-2b-itQwen3-1.7B - 4,0 tok/s Generation, 43 tok/s Prefill, TTFT 239.322 ms (3 Laufe)Qwen3-1.7BQwen2.5-3B-Instruct - 3,5 tok/s Generation, 30 tok/s Prefill, TTFT 277.455 ms (3 Laufe)Qwen2.5-3B-InstructSmolLM2-1.7B-Instruct - 3,1 tok/s Generation, 41 tok/s Prefill, TTFT 181.689 ms (2 Laufe)SmolLM2-1.7B-InstructLlama-3.2-3B-Instruct - 2,5 tok/s Generation, 29 tok/s Prefill, TTFT 270.941 ms (3 Laufe)Llama-3.2-3B-InstructQwen3-8B - 1,6 tok/s Generation, 9 tok/s Prefill, TTFT 232.748 ms (1 Lauf)Qwen3-8BMeta-Llama-3.1-8B-Instruct - 1,2 tok/s Generation, 8 tok/s Prefill, TTFT 340.594 ms (2 Laufe)Meta-Llama-3.1-8B-Ins...Qwen3-4B - 0,9 tok/s Generation, 11 tok/s Prefill, TTFT 324.617 ms (2 Laufe)Qwen3-4B
Qwen2.5-0.5B-Instruct 19,6 tok/sLlama-3.2-1B-Instruct 13,2 tok/sQwen2.5-1.5B-Instruct 9,1 tok/sQwen3-0.6B 8,0 tok/sgemma-2-2b-it 7,9 tok/sQwen3-1.7B 4,0 tok/sQwen2.5-3B-Instruct 3,5 tok/sSmolLM2-1.7B-Instruct 3,1 tok/sLlama-3.2-3B-Instruct 2,5 tok/sQwen3-8B 1,6 tok/sMeta-Llama-3.1-8B-Instruct 1,2 tok/sQwen3-4B 0,9 tok/s

ENGnach Engine

21,620,619,618,717,752545658Prefill (tok/s)Generation (tok/s)llama.cpp - 19,6 tok/s Generation, 55 tok/s Prefill, TTFT 216.068 ms (31 Laufe)llama.cpp
llama.cpp 19,6 tok/s

GPUnach Grafikkarte

21,620,619,618,717,752545658Prefill (tok/s)Generation (tok/s)CPU-only - 19,6 tok/s Generation, 55 tok/s Prefill, TTFT 216.068 ms (31 Laufe)CPU-only
CPU-only 19,6 tok/s
Durchsatz & Latenz

Performancebenchmark

31 veroeffentlichte Performance-Läufe auf 4 x Cortex-A78C + 4 x Cortex-A55.

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1Qwen2.5-0.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
19,64 tok/s TG
Prefill 135 · TTFT 103.828 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
2Qwen2.5-0.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
19,33 tok/s TG
Prefill 171 · TTFT 178.576 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
3Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
13,17 tok/s TG
Prefill 122 · TTFT 228.054 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
4Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,93 tok/s TG
Prefill 95 · TTFT 136.105 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
5Qwen2.5-0.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
11,74 tok/s TG
Prefill 85 · TTFT 29.146 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
6Qwen2.5-1.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,14 tok/s TG
Prefill 67 · TTFT 194.902 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
7Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
8,04 tok/s TG
Prefill 108 · TTFT 227.805 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
8gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,94 tok/s TG
Prefill 52 · TTFT 404.593 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
9gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,49 tok/s TG
Prefill 35 · TTFT 283.919 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
10Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,43 tok/s TG
Prefill 83 · TTFT 139.346 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
11Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,33 tok/s TG
Prefill 65 · TTFT 38.290 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
12Qwen2.5-1.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,93 tok/s TG
Prefill 47 · TTFT 52.732 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
13Qwen2.5-1.5B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,11 tok/s TG
Prefill 91 · TTFT 301.409 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
14Qwen3-1.7B1.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,04 tok/s TG
Prefill 48 · TTFT 383.019 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
15Qwen3-1.7B1.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,82 tok/s TG
Prefill 39 · TTFT 274.809 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
16gemma-2-2b-it2BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,76 tok/s TG
Prefill 31 · TTFT 59.057 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
17Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,47 tok/s TG
Prefill 33 · TTFT 369.084 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
18Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,22 tok/s TG
Prefill 24 · TTFT 103.262 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
19Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,17 tok/s TG
Prefill 80 · TTFT 30.662 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
20SmolLM2-1.7B-Instruct1.7BHuggingFaceTB PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,10 tok/s TG
Prefill 45 · TTFT 281.637 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
21Qwen3-1.7B1.7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,95 tok/s TG
Prefill 41 · TTFT 60.139 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
22SmolLM2-1.7B-Instruct1.7BHuggingFaceTB PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,89 tok/s TG
Prefill 38 · TTFT 81.741 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
23Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,46 tok/s TG
Prefill 35 · TTFT 360.878 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
24Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,99 tok/s TG
Prefill 22 · TTFT 104.643 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
25Qwen3-8B8.2BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,62 tok/s TG
Prefill 9 · TTFT 232.748 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
26Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,19 tok/s TG
Prefill 9 · TTFT 227.569 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
27Qwen3-4B4BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,91 tok/s TG
Prefill 15 · TTFT 142.282 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
28Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,09 tok/s TG
Prefill 31 · TTFT 347.304 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
29Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,07 tok/s TG
Prefill 33 · TTFT 360.019 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
30Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,02 tok/s TG
Prefill 7 · TTFT 453.619 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
31Qwen3-4B4BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,01 tok/s TG
Prefill 6 · TTFT 506.953 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
Agent- & Chat-Bewertung

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf 4 x Cortex-A78C + 4 x Cortex-A55.

Im Leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← Alle Hardware

Technische Daten

Technische Daten – 4 x Cortex-A78C + 4 x Cortex-A55

HerstellerUnbekannt
Beste Generation19,6 tok/s
Bester Prefill171 tok/s
Modelle12
Messläufe (Performance)31