Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Anmelden Registrieren
Beta
🧮
Mainboard

Dell Inc. PowerEdge R820

Dell2 CPUs77 Benchmarks⚡ 10 W Idle
CPUs
2
Modelle
26
Benchmarks
77
Beste Generation
259,9 tok/s
🏆
Qwen2.5-3B-Instruct läuft am schnellsten auf diesem Board · 259,9 tok/s
26 Modelle mit Performance-Daten getestet

Top-Modelle nach Token-Generierung

Bester gemessener Generierungs-Durchsatz je Modell auf Dell Inc. PowerEdge R820 (tok/s) – klicken für Leaderboard-Filter.

Qwen2.5-3B-Instruct3B
259,9 tok/s
Llama-3.2-3B-Instruct3B
226,6 tok/s
Meta-Llama-3.1-8B-Instruct8B
169,0 tok/s
Qwen2.5-7B-Instruct7B
160,3 tok/s
gemma-4-E2B-it5B
54,7 tok/s
Qwen3.6-35B-A3B35B
27,5 tok/s
Nemotron-3-Nano-30B-A3B30B
15,1 tok/s
gpt-oss-20b20B
14,5 tok/s
Qwen3-30B-A3B-Thinking-250730B
8,5 tok/s
Nemotron-3-Nano-4B4B
8,0 tok/s
Qwen3-30B-A3B-Instruct-250730B
7,1 tok/s
Qwen3.5-122B-A10B122B
7,1 tok/s
Anzeige
Modell-Vergleich

Getestete Modelle im Vergleich

Jede Blase ist ein Modell auf Dell Inc. PowerEdge R820 – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.

MODnach Modell

33825316984,40,002.8635.7258.588Prefill (tok/s)Generation (tok/s)Qwen2.5-3B-Instruct - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe)Qwen2.5-3B-InstructLlama-3.2-3B-Instruct - 226,6 tok/s Generation, 6.927 tok/s Prefill, TTFT 2.004 ms (6 Laufe)Llama-3.2-3B-InstructMeta-Llama-3.1-8B-Instruct - 169,0 tok/s Generation, 1.632 tok/s Prefill, TTFT 21.610 ms (4 Laufe)Meta-Llama-3.1-8B-Ins...Qwen2.5-7B-Instruct - 160,3 tok/s Generation, 3.649 tok/s Prefill, TTFT 3.816 ms (3 Laufe)Qwen2.5-7B-Instructgemma-4-E2B-it - 54,7 tok/s Generation, 3.248 tok/s Prefill, TTFT 2.994 ms (3 Laufe)gemma-4-E2B-itQwen3.6-35B-A3B - 27,5 tok/s Generation, 62 tok/s Prefill, TTFT 143.472 ms (4 Laufe)Qwen3.6-35B-A3BNemotron-3-Nano-30B-A3B - 15,1 tok/s Generation, 54 tok/s Prefill, TTFT 207.499 ms (6 Laufe)Nemotron-3-Nano-30B-A...gpt-oss-20b - 14,5 tok/s Generation, 88 tok/s Prefill, TTFT 122.346 ms (3 Laufe)gpt-oss-20bQwen3-30B-A3B-Thinking-2507 - 8,5 tok/s Generation, 74 tok/s Prefill, TTFT 134.321 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Nemotron-3-Nano-4B - 8,0 tok/s Generation, 63 tok/s Prefill, TTFT 139.289 ms (3 Laufe)Nemotron-3-Nano-4BQwen3-30B-A3B-Instruct-2507 - 7,1 tok/s Generation, 102 tok/s Prefill, TTFT 109.338 ms (3 Laufe)Qwen3-30B-A3B-Instruc...Qwen3.5-122B-A10B - 7,1 tok/s Generation, 8 tok/s Prefill, TTFT 236.831 ms (1 Lauf)Qwen3.5-122B-A10Bgpt-oss-120b - 6,8 tok/s Generation, 35 tok/s Prefill, TTFT 157.060 ms (4 Laufe)gpt-oss-120bQwen3-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-Cascade-2-30B-A3B - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)Nemotron-Cascade-2-30...North-Mini-Code-1.0 - 5,1 tok/s Generation, 89 tok/s Prefill, TTFT 113.797 ms (3 Laufe)North-Mini-Code-1.0GLM-4.5-Air - 4,2 tok/s Generation, 14 tok/s Prefill, TTFT 172.204 ms (2 Laufe)GLM-4.5-AirSeed-OSS-36B-Instruct - 3,4 tok/s Generation, 31 tok/s Prefill, TTFT 201.501 ms (3 Laufe)Seed-OSS-36B-InstructMiniMax-M2.7 - 2,6 tok/s Generation, 24 tok/s Prefill, TTFT 193.311 ms (3 Laufe)MiniMax-M2.7OpenReasoning-Nemotron-32B - 2,4 tok/s Generation, 33 tok/s Prefill, TTFT 213.110 ms (3 Laufe)OpenReasoning-Nemotro...Qwen2.5-72B-Instruct - 2,3 tok/s Generation, 81 tok/s Prefill, TTFT 569 ms (2 Laufe)Qwen2.5-72B-InstructQwen2.5-Coder-32B-Instruct - 2,3 tok/s Generation, 53 tok/s Prefill, TTFT 145.743 ms (2 Laufe)Qwen2.5-Coder-32B-Ins...DeepSeek-V4-Flash-284B-A13B - 1,2 tok/s Generation, 14 tok/s Prefill, TTFT 148.315 ms (1 Lauf)DeepSeek-V4-Flash-284...Llama-3.3-Nemotron-Super-49B-v1.5 - 1,1 tok/s Generation, 21 tok/s Prefill, TTFT 117.641 ms (1 Lauf)Llama-3.3-Nemotron-Su...Nemotron-H-47B-Reasoning-128K - 1,1 tok/s Generation, 16 tok/s Prefill, TTFT 141.049 ms (1 Lauf)Nemotron-H-47B-Reason...MiniMax-M2.5 - 0,8 tok/s Generation, 22 tok/s Prefill, TTFT 98.716 ms (1 Lauf)MiniMax-M2.5
Qwen2.5-3B-Instruct 259,9 tok/sLlama-3.2-3B-Instruct 226,6 tok/sMeta-Llama-3.1-8B-Instruct 169,0 tok/sQwen2.5-7B-Instruct 160,3 tok/sgemma-4-E2B-it 54,7 tok/sQwen3.6-35B-A3B 27,5 tok/sNemotron-3-Nano-30B-A3B 15,1 tok/sgpt-oss-20b 14,5 tok/sQwen3-30B-A3B-Thinking-2507 8,5 tok/sNemotron-3-Nano-4B 8,0 tok/sQwen3-30B-A3B-Instruct-2507 7,1 tok/sQwen3.5-122B-A10B 7,1 tok/sgpt-oss-120b 6,8 tok/sQwen3-Coder-30B-A3B-Instruct 6,7 tok/sNemotron-Cascade-2-30B-A3B 5,9 tok/sNorth-Mini-Code-1.0 5,1 tok/sGLM-4.5-Air 4,2 tok/sSeed-OSS-36B-Instruct 3,4 tok/sMiniMax-M2.7 2,6 tok/sOpenReasoning-Nemotron-32B 2,4 tok/sQwen2.5-72B-Instruct 2,3 tok/sQwen2.5-Coder-32B-Instruct 2,3 tok/sDeepSeek-V4-Flash-284B-A13B 1,2 tok/sLlama-3.3-Nemotron-Super-49B-v1.5 1,1 tok/sNemotron-H-47B-Reasoning-128K 1,1 tok/sMiniMax-M2.5 0,8 tok/s

Prozessoren auf diesem Board

CPUIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHzIntel · 39 Läufe259,9 tok/s CPUIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHzIntel · 38 Läufe14,5 tok/s

Grafikkarten auf diesem Board

GPU2x NVIDIA GeForce RTX 2060NVIDIA · 39 Läufe259,9 tok/s

Getestete Modelle

MQwen2.5-3B-Instruct3BQwen (Alibaba) · 6 Läufe MLlama-3.2-3B-Instruct3BMeta · 6 Läufe MMeta-Llama-3.1-8B-Instruct8BMeta · 4 Läufe MQwen2.5-7B-Instruct7BQwen (Alibaba) · 3 Läufe Mgemma-4-E2B-it5BGoogle · 3 Läufe MQwen3.6-35B-A3B35BQwen (Alibaba) · 4 Läufe MNemotron-3-Nano-30B-A3B30BNVIDIA · 6 Läufe Mgpt-oss-20b20BOpenAI · 3 Läufe MQwen3-30B-A3B-Thinking-250730BQwen (Alibaba) · 3 Läufe MNemotron-3-Nano-4B4BNVIDIA · 3 Läufe MQwen3-30B-A3B-Instruct-250730BQwen (Alibaba) · 3 Läufe MQwen3.5-122B-A10B122BQwen (Alibaba) · 1 Läufe Mgpt-oss-120b120BOpenAI · 4 Läufe MQwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) · 3 Läufe MNemotron-Cascade-2-30B-A3B30BNVIDIA · 3 Läufe MNorth-Mini-Code-1.0Cohere · 3 Läufe MGLM-4.5-Air106BZ.ai (Zhipu) · 2 Läufe MSeed-OSS-36B-Instruct36BByteDance Seed · 3 Läufe MMiniMax-M2.7230BMiniMax · 3 Läufe MOpenReasoning-Nemotron-32B32BNVIDIA · 3 Läufe MQwen2.5-72B-Instruct72BQwen (Alibaba) · 2 Läufe MQwen2.5-Coder-32B-Instruct32BQwen (Alibaba) · 2 Läufe MDeepSeek-V4-Flash-284B-A13B284BDeepSeek · 1 Läufe MLlama-3.3-Nemotron-Super-49B-v1.549BNVIDIA · 1 Läufe MNemotron-H-47B-Reasoning-128K47BNVIDIA · 1 Läufe MMiniMax-M2.5230BMiniMax · 1 Läufe

Genutzte Betriebssysteme

🖥Ubuntu 24.04.3 LTS (Kernel 7.0.0-28-generic)
Durchsatz & Latenz

Performancebenchmark

77 veroeffentlichte Performance-Läufe auf Dell Inc. PowerEdge R820.

Im Leaderboard →
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
259,86 tok/s TG
Prefill 9.253 · TTFT 3.361 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
2Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
226,59 tok/s TG
Prefill 9.526 · TTFT 3.488 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
3Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
225,82 tok/s TG
Prefill 9.739 · TTFT 3.277 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
4Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
215,97 tok/s TG
Prefill 9.775 · TTFT 3.283 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
5Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
187,50 tok/s TG
Prefill 6.698 · TTFT 2.090 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
6Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
173,08 tok/s TG
Prefill 7.158 · TTFT 2.024 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
7Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
168,96 tok/s TG
Prefill 3.010 · TTFT 18.082 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMvLLMgodclawAWQDetails →
8Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
168,19 tok/s TG
Prefill 7.879 · TTFT 1.850 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
9Qwen2.5-7B-Instruct7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
160,26 tok/s TG
Prefill 4.979 · TTFT 6.510 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
10Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
158,90 tok/s TG
Prefill 7.616 · TTFT 1.908 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
11Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
122,88 tok/s TG
Prefill 2.387 · TTFT 7.059 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMvLLMgodclawAWQDetails →
12Qwen2.5-7B-Instruct7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
108,79 tok/s TG
Prefill 3.816 · TTFT 3.796 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
13Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
106,40 tok/s TG
Prefill 3.776 · TTFT 651 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
14Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
100,62 tok/s TG
Prefill 3.646 · TTFT 677 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
15Qwen2.5-3B-Instruct3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
73,93 tok/s TG
Prefill 4.119 · TTFT 596 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
16Llama-3.2-3B-Instruct3BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
70,69 tok/s TG
Prefill 3.840 · TTFT 645 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
17Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
61,51 tok/s TG
Prefill 1.097 · TTFT 2.256 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMvLLMgodclawAWQDetails →
18Qwen2.5-7B-Instruct7BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
56,92 tok/s TG
Prefill 2.151 · TTFT 1.142 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
19gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
54,70 tok/s TG
Prefill 3.624 · TTFT 5.459 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
20gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
50,91 tok/s TG
Prefill 3.620 · TTFT 2.732 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
21gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
37,14 tok/s TG
Prefill 2.500 · TTFT 791 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ8_0Details →
22Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
27,51 tok/s TG
Prefill 79 · TTFT 326.271 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
23Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
23,06 tok/s TG
Prefill 56 · TTFT 178.109 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
24Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
19,35 tok/s TG
Prefill 51 · TTFT 38.075 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
25Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
15,11 tok/s TG
Prefill 29 · TTFT 379.775 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
26gpt-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 →
27Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
13,88 tok/s TG
Prefill 24 · TTFT 89.272 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
28gpt-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 →
29Qwen3-30B-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 →
30Nemotron-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 →
31Qwen3-30B-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 →
32Qwen3.5-122B-A10B122BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
7,07 tok/s TG
Prefill 8 · TTFT 236.831 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
33gpt-oss-120b120BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
6,79 tok/s TG
Prefill 16 · TTFT 131.537 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
34Qwen3-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 →
35Qwen3-30B-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 →
36Nemotron-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 →
37gpt-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 →
38Qwen3-30B-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 →
39Qwen3-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 →
40Nemotron-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 →
41Nemotron-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 →
42Nemotron-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 →
43gpt-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 →
44North-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 →
45Nemotron-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 →
46gpt-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 →
47Qwen3.6-35B-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 →
48North-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 →
49GLM-4.5-Air106BZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,18 tok/s TG
Prefill 10 · TTFT 226.444 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
50Meta-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 →
51Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,44 tok/s TG
Prefill 39 · TTFT 317.771 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
52Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
3,22 tok/s TG
Prefill 54 · TTFT 382.793 ms
10×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
53North-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 →
54MiniMax-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 →
55OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,44 tok/s TG
Prefill 39 · TTFT 324.717 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
56Qwen2.5-72B-Instruct72BQwen (Alibaba) PerformancebenchmarkPerformancetest Small 1.0
2,28 tok/s TG
Prefill 81 · TTFT 569 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
57Qwen2.5-72B-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 →
58Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
2,27 tok/s TG
Prefill 62 · TTFT 233.464 ms
5×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
59GLM-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 →
60Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,63 tok/s TG
Prefill 47 · TTFT 45.942 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
61OpenReasoning-Nemotron-32B32BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,57 tok/s TG
Prefill 51 · TTFT 47.947 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
62Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,54 tok/s TG
Prefill 44 · TTFT 58.023 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
63DeepSeek-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 →
64Llama-3.3-Nemotron-Super-49B-v1.549BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,14 tok/s TG
Prefill 21 · TTFT 117.641 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
65Nemotron-H-47B-Reasoning-128K47BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1,12 tok/s TG
Prefill 16 · TTFT 141.049 ms
1×2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
66OpenReasoning-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 →
67Qwen3-30B-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 →
68Qwen3-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 →
69Seed-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 →
70MiniMax-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 →
71Qwen3-30B-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 →
72Nemotron-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 →
73Nemotron-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 →
74Nemotron-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 →
75gpt-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 →
76MiniMax-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 →
77MiniMax-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 →
Agent- & Chat-Bewertung

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf Dell Inc. PowerEdge R820.

Im Leaderboard →
Noch keine Harnessbenchmarks auf diesem Mainboard.

← Alle Hardware