Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🎮
Grafikkarte

Keine GPU (CPU-only)

Other
78Benchmarks
29Modelle
78Performance
0Harness
Beste Generation
70,9 tok/s
gpt-oss-20b
∅ Generation
7,3 tok/s
Schnitt aus 78 Läufen
Bester Prefill
273 tok/s
Prompt-Verarbeitung
Bester TTFT
569 ms
Time to First Token
Beste Harness-Quote
–%
noch kein Harness
🏆
gpt-oss-20b läuft am schnellsten auf dieser GPU · 70,9 tok/s
Bester Prefill: 273 tok/s · 29 Modelle getestet

Top-Modelle

Bester gemessener Durchsatz je Modell auf Keine GPU (CPU-only) – umschaltbar nach Generation, Prefill oder Kombiwert.

gpt-oss-20b20B
70,9 tok/s
Qwen3-30B-A3B-Instruct-250730B
31,2 tok/s
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
Qwen3-30B-A3B-Thinking-250730B
8,5 tok/s
Nemotron-3-Nano-4B4B
8,0 tok/s
Qwen3-0.6B0.6B
8,0 tok/s
gemma-2-2b-it2B
7,9 tok/s
Qwen3-Coder-30B-A3B-Instruct30B
6,7 tok/s
Anzeige
Performanceprofil

Durchsatz auf Keine GPU (CPU-only)

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

MODnach Modell

91,969,046,023,00,0065130195Prefill (tok/s)Generation (tok/s)gpt-oss-20b - 70,9 tok/s Generation, 119 tok/s Prefill, TTFT 95.764 ms (6 Laufe)gpt-oss-20bQwen3-30B-A3B-Instruct-2507 - 31,2 tok/s Generation, 158 tok/s Prefill, TTFT 85.238 ms (6 Laufe)Qwen3-30B-A3B-Instruc...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, 119 tok/s Prefill, TTFT 103.809 ms (4 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-InstructQwen3-30B-A3B-Thinking-2507 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Qwen3-0.6B - 8,0 tok/s Generation, 74 tok/s Prefill, TTFT 126.155 ms (4 Laufe)Qwen3-0.6BNemotron-3-Nano-4B - 8,0 tok/s Generation, 63 tok/s Prefill, TTFT 139.289 ms (3 Laufe)Nemotron-3-Nano-4Bgemma-2-2b-it - 7,9 tok/s Generation, 40 tok/s Prefill, TTFT 249.190 ms (3 Laufe)gemma-2-2b-itQwen3-Coder-30B-A3B-Instruct - 6,7 tok/s Generation, 103 tok/s Prefill, TTFT 107.342 ms (3 Laufe)Qwen3-Coder-30B-A3B-I...Nemotron-3-Nano-30B-A3B - 6,6 tok/s Generation, 72 tok/s Prefill, TTFT 131.051 ms (3 Laufe)Nemotron-3-Nano-30B-A...Nemotron-Cascade-2-30B-A3B - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)Nemotron-Cascade-2-30...gpt-oss-120b - 5,3 tok/s Generation, 42 tok/s Prefill, TTFT 165.568 ms (3 Laufe)gpt-oss-120bNorth-Mini-Code-1.0 - 5,1 tok/s Generation, 89 tok/s Prefill, TTFT 113.797 ms (3 Laufe)North-Mini-Code-1.0Qwen3.6-35B-A3B - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)Qwen3.6-35B-A3BQwen3-1.7B - 4,0 tok/s Generation, 43 tok/s Prefill, TTFT 239.322 ms (3 Laufe)Qwen3-1.7BMeta-Llama-3.1-8B-Instruct - 3,6 tok/s Generation, 17 tok/s Prefill, TTFT 246.744 ms (3 Laufe)Meta-Llama-3.1-8B-Ins...Qwen2.5-3B-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-InstructMiniMax-M2.7 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe)MiniMax-M2.7Llama-3.2-3B-Instruct - 2,5 tok/s Generation, 29 tok/s Prefill, TTFT 270.941 ms (3 Laufe)Llama-3.2-3B-InstructQwen2.5-72B-Instruct - 2,3 tok/s Generation, 81 tok/s Prefill, TTFT 569 ms (1 Lauf)Qwen2.5-72B-InstructGLM-4.5-Air - 2,1 tok/s Generation, 18 tok/s Prefill, TTFT 117.963 ms (1 Lauf)GLM-4.5-AirQwen3-8B - 1,6 tok/s Generation, 9 tok/s Prefill, TTFT 232.748 ms (1 Lauf)Qwen3-8BQwen3-4B - 1,3 tok/s Generation, 8 tok/s Prefill, TTFT 374.500 ms (3 Laufe)Qwen3-4BDeepSeek-V4-Flash-284B-A13B - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)DeepSeek-V4-Flash-284...OpenReasoning-Nemotron-32B - 1,1 tok/s Generation, 8 tok/s Prefill, TTFT 266.668 ms (1 Lauf)OpenReasoning-Nemotro...Seed-OSS-36B-Instruct - 1,0 tok/s Generation, 8 tok/s Prefill, TTFT 240.790 ms (1 Lauf)Seed-OSS-36B-InstructMiniMax-M2.5 - 0,8 tok/s Generation, 22 tok/s Prefill, TTFT 98.716 ms (1 Lauf)MiniMax-M2.5
gpt-oss-20b 70,9 tok/sQwen3-30B-A3B-Instruct-2507 31,2 tok/sQwen2.5-0.5B-Instruct 19,6 tok/sLlama-3.2-1B-Instruct 13,2 tok/sQwen2.5-1.5B-Instruct 9,1 tok/sQwen3-30B-A3B-Thinking-2507 8,5 tok/sQwen3-0.6B 8,0 tok/sNemotron-3-Nano-4B 8,0 tok/sgemma-2-2b-it 7,9 tok/sQwen3-Coder-30B-A3B-Instruct 6,7 tok/sNemotron-3-Nano-30B-A3B 6,6 tok/sNemotron-Cascade-2-30B-A3B 5,9 tok/sgpt-oss-120b 5,3 tok/sNorth-Mini-Code-1.0 5,1 tok/sQwen3.6-35B-A3B 4,3 tok/sQwen3-1.7B 4,0 tok/sMeta-Llama-3.1-8B-Instruct 3,6 tok/sQwen2.5-3B-Instruct 3,5 tok/sSmolLM2-1.7B-Instruct 3,1 tok/sMiniMax-M2.7 2,6 tok/sLlama-3.2-3B-Instruct 2,5 tok/sQwen2.5-72B-Instruct 2,3 tok/sGLM-4.5-Air 2,1 tok/sQwen3-8B 1,6 tok/sQwen3-4B 1,3 tok/sDeepSeek-V4-Flash-284B-A13B 1,2 tok/sOpenReasoning-Nemotron-32B 1,1 tok/sSeed-OSS-36B-Instruct 1,0 tok/sMiniMax-M2.5 0,8 tok/s

ENGnach Engine

91,668,745,822,90,063717988Prefill (tok/s)Generation (tok/s)llama.cpp - 70,9 tok/s Generation, 70 tok/s Prefill, TTFT 164.751 ms (77 Laufe)llama.cppunbekannt - 2,3 tok/s Generation, 81 tok/s Prefill, TTFT 569 ms (1 Lauf)unbekannt
llama.cpp 70,9 tok/sunbekannt 2,3 tok/s

CPUnach Prozessor

91,368,545,722,80,02186151216Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 70,9 tok/s Generation, 182 tok/s Prefill, TTFT 65.160 ms (6 Laufe)AMD Ryzen Threadrippe...4 x Cortex-A78C + 4 x Cortex-A55 - 19,6 tok/s Generation, 55 tok/s Prefill, TTFT 216.068 ms (31 Laufe)4 x Cortex-A78C + 4 x...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 14,5 tok/s Generation, 64 tok/s Prefill, TTFT 131.670 ms (38 Laufe)Intel(R) Xeon(R) CPU ...AMD Jaguar 8-Core (PlayStation 4) - 3,9 tok/s Generation, 73 tok/s Prefill, TTFT 197.952 ms (3 Laufe)AMD Jaguar 8-Core (Pl...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 70,9 tok/s4 x Cortex-A78C + 4 x Cortex-A55 19,6 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 14,5 tok/sAMD Jaguar 8-Core (PlayStation 4) 3,9 tok/s
Durchsatz & Latenz

Performancebenchmark

78 veroeffentlichte Performance-Läufe auf Keine GPU (CPU-only).

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
70,85 tok/s TG
Prefill 154 · TTFT 129.121 ms
10×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
2gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
53,48 tok/s TG
Prefill 153 · TTFT 64.583 ms
5×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
3Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
31,23 tok/s TG
Prefill 273 · TTFT 107.591 ms
10×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_MDetails →
4gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
28,43 tok/s TG
Prefill 143 · TTFT 13.839 ms
1×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawMXFP4Details →
5Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
25,98 tok/s TG
Prefill 218 · TTFT 59.755 ms
5×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_MDetails →
6Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
24,50 tok/s TG
Prefill 152 · TTFT 16.071 ms
1×Keine GPU (CPU-only) iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_MDetails →
7Qwen2.5-0.5B-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 →
8Qwen2.5-0.5B-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 →
9gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
14,47 tok/s TG
Prefill 97 · TTFT 222.547 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
10Llama-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 →
11Llama-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 →
12Qwen2.5-0.5B-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 →
13gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,77 tok/s TG
Prefill 89 · TTFT 119.492 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
14Qwen2.5-1.5B-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 →
15Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
8,52 tok/s TG
Prefill 71 · TTFT 152.830 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
16Qwen3-0.6B0.6BQwen (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 →
17Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,97 tok/s TG
Prefill 72 · TTFT 153.653 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
18gemma-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 →
19gemma-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 →
20Qwen3-0.6B0.6BQwen (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 →
21Llama-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 →
22Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,14 tok/s TG
Prefill 69 · TTFT 35.318 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
23Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,74 tok/s TG
Prefill 74 · TTFT 32.942 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
24Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,64 tok/s TG
Prefill 73 · TTFT 33.548 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
25Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,60 tok/s TG
Prefill 73 · TTFT 150.849 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
26gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,46 tok/s TG
Prefill 79 · TTFT 25.000 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
27Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,09 tok/s TG
Prefill 100 · TTFT 121.223 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
28Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,05 tok/s TG
Prefill 104 · TTFT 116.729 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
29Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,88 tok/s TG
Prefill 61 · TTFT 35.422 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
30Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,86 tok/s TG
Prefill 61 · TTFT 35.481 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
31Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,33 tok/s TG
Prefill 74 · TTFT 150.609 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
32gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,29 tok/s TG
Prefill 56 · TTFT 189.966 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
33North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
5,05 tok/s TG
Prefill 71 · TTFT 28.002 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
34Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,94 tok/s TG
Prefill 41 · TTFT 62.079 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
35Qwen2.5-1.5B-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 →
36gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,46 tok/s TG
Prefill 50 · TTFT 39.304 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
37Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,29 tok/s TG
Prefill 62 · TTFT 31.435 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
38North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,20 tok/s TG
Prefill 86 · TTFT 127.307 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
39Qwen2.5-1.5B-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 →
40Qwen3-1.7B1.7BQwen (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 →
41Llama-3.2-1B-Instruct1BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,91 tok/s TG
Prefill 193 · TTFT 12.786 ms
1×Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_MDetails →
42Qwen3-1.7B1.7BQwen (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 →
43Qwen3-0.6B0.6BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,80 tok/s TG
Prefill 23 · TTFT 106.805 ms
1×Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_MDetails →
44gemma-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 →
45Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,55 tok/s TG
Prefill 36 · TTFT 59.044 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
46Qwen2.5-3B-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 →
47Qwen2.5-3B-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 →
48Qwen3-0.6B0.6BQwen (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 →
49North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,16 tok/s TG
Prefill 109 · TTFT 186.084 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
50SmolLM2-1.7B-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 →
51Qwen3-1.7B1.7BQwen (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 →
52SmolLM2-1.7B-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 →
53MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,62 tok/s TG
Prefill 15 · TTFT 156.050 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
54Llama-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 →
55Qwen2.5-72B-Instruct72BQwen (Alibaba) Performancebenchmark
2,28 tok/s TG
Prefill 81 · TTFT 569 ms
1×Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMgodclawDetails →
56GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,13 tok/s TG
Prefill 18 · TTFT 117.963 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
57Llama-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 →
58Qwen3-8B8.2BQwen (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 →
59Qwen3-4B4BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,25 tok/s TG
Prefill 4 · TTFT 474.264 ms
1×Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_MDetails →
60DeepSeek-V4-Flash-284B-A13B284BDeepSeek PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,20 tok/s TG
Prefill 14 · TTFT 148.315 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_XLDetails →
61Meta-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 →
62OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,10 tok/s TG
Prefill 8 · TTFT 266.668 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
63Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,04 tok/s TG
Prefill 137 · TTFT 171.473 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
64Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,99 tok/s TG
Prefill 130 · TTFT 172.354 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
65Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,97 tok/s TG
Prefill 8 · TTFT 240.790 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
66Qwen3-4B4BQwen (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 →
67MiniMax-M2.5230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,84 tok/s TG
Prefill 22 · TTFT 98.716 ms
1×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
68Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,58 tok/s TG
Prefill 77 · TTFT 216.585 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
69Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,27 tok/s TG
Prefill 81 · TTFT 206.882 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
70Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,27 tok/s TG
Prefill 82 · TTFT 204.776 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
71Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,25 tok/s TG
Prefill 75 · TTFT 202.135 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
72Llama-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 →
73Qwen2.5-3B-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 →
74gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,05 tok/s TG
Prefill 20 · TTFT 267.436 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
75MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,04 tok/s TG
Prefill 29 · TTFT 211.132 ms
5×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
76MiniMax-M2.7230BMiniMax PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
0,03 tok/s TG
Prefill 28 · TTFT 212.753 ms
10×Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAMllama.cppgodclawUD-Q4_K_MDetails →
77Meta-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 →
78Qwen3-4B4BQwen (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 Keine GPU (CPU-only).

Im Leaderboard →
Noch keine Harnessbenchmarks auf dieser Hardware.

← Alle Hardware

Technische Daten

Technische Daten – Keine GPU (CPU-only)

HerstellerOther
Beste Generation70,9 tok/s
Bester Prefill273 tok/s
Modelle29
Messläufe (Performance)78