Created bymario-alka.dePowered bynoob2claw.detricoma.de
🧮
Mainboard

ASRockRack ROMED8-2T/BCM

ASRock1 CPU21 Benchmarks
CPUs
1
Models
3
Benchmarks
21
Best generation
388,1 tok/s
🏆
Ling-3.0-flash läuft am schnellsten auf diesem Board · 388,1 tok/s
3 Modelle mit Performance-Daten getestet

Top models by token generation

Bester gemessener Generierungs-Durchsatz je Modell auf ASRockRack ROMED8-2T/BCM (tok/s) – klicken für Leaderboard-Filter.

Ling-3.0-flash127.5B
388,1 tok/s
Qwen3.8-Flash-Next180B
79,2 tok/s
Anzeige
Model comparison

Tested models compared

Jede Blase ist ein Modell auf ASRockRack ROMED8-2T/BCM – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.

MODnach Modell

4893662441220,004.4288.85613.284Prefill (tok/s)Generation (tok/s)Ling-3.0-flash - 388,1 tok/s Generation, 4.550 tok/s Prefill, TTFT 4.923 ms (9 Laufe)Ling-3.0-flashMeta-Llama-3.1-8B-Instruct - 317,0 tok/s Generation, 10.774 tok/s Prefill, TTFT 1.374 ms (3 Laufe)Meta-Llama-3.1-8B-Ins...Qwen3.8-Flash-Next - 79,2 tok/s Generation, 423 tok/s Prefill, TTFT 24.603 ms (9 Laufe)Qwen3.8-Flash-Next
Ling-3.0-flash 388,1 tok/sMeta-Llama-3.1-8B-Instruct 317,0 tok/sQwen3.8-Flash-Next 79,2 tok/s

Tested models

Throughput & latency

Performancebenchmark

21 veroeffentlichte Performance-Läufe auf ASRockRack ROMED8-2T/BCM.

In the leaderboard →
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
388,05 tok/s TG
Prefill 16.198 · TTFT 2.053 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMvLLMgodclawINT4
2Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
343,90 tok/s TG
Prefill 9.629 · TTFT 1.973 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMvLLMgodclawINT4
3Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
317,00 tok/s TG
Prefill 14.849 · TTFT 2.492 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 126 GB RAMvLLMgodclaw
4Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
201,32 tok/s TG
Prefill 2.330 · TTFT 11.380 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
5Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
197,94 tok/s TG
Prefill 2.288 · TTFT 11.557 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawQ4_K_M
6Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
190,45 tok/s TG
Prefill 1.680 · TTFT 6.722 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
7Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
190,09 tok/s TG
Prefill 1.655 · TTFT 6.827 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawQ4_K_M
8Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
183,35 tok/s TG
Prefill 11.565 · TTFT 1.219 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 126 GB RAMvLLMgodclaw
9Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,60 tok/s TG
Prefill 4.438 · TTFT 606 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMvLLMgodclawINT4
10Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
90,29 tok/s TG
Prefill 1.380 · TTFT 1.577 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
11Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
89,66 tok/s TG
Prefill 1.349 · TTFT 1.612 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawQ4_K_M
12Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
79,19 tok/s TG
Prefill 670 · TTFT 33.965 ms
10×2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAMllama.cppgodclawUD-Q4_K_XL
13Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
73,30 tok/s TG
Prefill 487 · TTFT 20.813 ms
5×2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAMllama.cppgodclawUD-Q4_K_XL
14Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
71,73 tok/s TG
Prefill 560 · TTFT 40.628 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawUD-Q4_K_XL
15Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
67,46 tok/s TG
Prefill 568 · TTFT 39.939 ms
10×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
16Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
60,89 tok/s TG
Prefill 409 · TTFT 24.788 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawUD-Q4_K_XL
17Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
55,85 tok/s TG
Prefill 415 · TTFT 24.406 ms
5×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
18Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
42,39 tok/s TG
Prefill 5.909 · TTFT 412 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 126 GB RAMvLLMgodclaw
19Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
38,84 tok/s TG
Prefill 258 · TTFT 10.963 ms
1×2x NVIDIA RTX A6000AMD EPYC 7203P 8-Core Processor · 126 GB RAMllama.cppgodclawUD-Q4_K_XL
20Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
36,99 tok/s TG
Prefill 221 · TTFT 12.961 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 252 GB RAMllama.cppgodclawUD-Q4_K_XL
21Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
35,58 tok/s TG
Prefill 220 · TTFT 12.963 ms
1×2x NVIDIA RTX A6000 iAMD EPYC 7203P 8-Core Processor · 110 GB RAMllama.cppgodclaw
Agent & chat rating

Harnessbenchmark

0 veroeffentlichte Harness-Läufe auf ASRockRack ROMED8-2T/BCM.

In the leaderboard →
Noch keine Harnessbenchmarks auf diesem Mainboard.

← All hardware