Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🌐
🧮
Mainboard

Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX)

Other1 CPU90 Benchmarks
CPUs
1
Modelle
27
Benchmarks
90
Beste Generation
173,3 tok/s
🏆
gpt-oss-20b läuft am schnellsten auf diesem Board · 173,3 tok/s
26 Modelle mit Performance-Daten getestet

Top-Modelle nach Token-Generierung

Bester gemessener Generierungs-Durchsatz je Modell auf Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) (tok/s) – klicken für Leaderboard-Filter.

gpt-oss-20b
173,3 tok/s
Qwen3.5-35B-A3B
109,7 tok/s
Modell-Vergleich

Getestete Modelle im Vergleich

Jede Blase ist ein Modell auf Meigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) – Position: Prompt-Verarbeitung (X) × Ausgabe-Geschwindigkeit (Y), Blasengröße: Anzahl Messläufe. Naeher an der oberen rechten Ecke = schneller.

MODnach Modell

22416811255,90,008041.6082.412Prefill (tok/s)Generation (tok/s)gpt-oss-20b - 173,3 tok/s Generation, 1.617 tok/s Prefill, TTFT 6.404 ms (3 Laufe)gpt-oss-20bNorth-Mini-Code-1.0 - 131,9 tok/s Generation, 1.427 tok/s Prefill, TTFT 7.438 ms (3 Laufe)North-Mini-Code-1.0Qwen3-30B-A3B-Thinking-2507 - 131,2 tok/s Generation, 1.375 tok/s Prefill, TTFT 8.315 ms (3 Laufe)Qwen3-30B-A3B-Thinkin...Gemma-4-26B-A4B-it - 119,5 tok/s Generation, 773 tok/s Prefill, TTFT 6.904 ms (5 Laufe)Gemma-4-26B-A4B-itNVIDIA-Nemotron-3-Nano-30B-A3B - 117,1 tok/s Generation, 1.161 tok/s Prefill, TTFT 9.086 ms (3 Laufe)NVIDIA-Nemotron-3-Nan...Qwen3-Coder-30B-A3B-Instruct - 115,8 tok/s Generation, 1.790 tok/s Prefill, TTFT 6.600 ms (3 Laufe)Qwen3-Coder-30B-A3B-I...Nemotron-Cascade-2-30B-A3B - 114,5 tok/s Generation, 1.173 tok/s Prefill, TTFT 8.896 ms (3 Laufe)Nemotron-Cascade-2-30...NVIDIA-Nemotron-3-Nano-4B - 113,4 tok/s Generation, 1.903 tok/s Prefill, TTFT 5.505 ms (3 Laufe)NVIDIA-Nemotron-3-Nan...Nemotron-3-Nano-Omni-30B-A3B-Reasoning - 112,4 tok/s Generation, 1.115 tok/s Prefill, TTFT 9.469 ms (3 Laufe)Nemotron-3-Nano-Omni-...Qwen3.5-35B-A3B - 109,7 tok/s Generation, 1.204 tok/s Prefill, TTFT 8.627 ms (3 Laufe)Qwen3.5-35B-A3BQwen3-30B-A3B-Instruct-2507 - 107,6 tok/s Generation, 1.878 tok/s Prefill, TTFT 6.589 ms (3 Laufe)Qwen3-30B-A3B-Instruc...Qwen-AgentWorld-35B-A3B - 103,8 tok/s Generation, 1.220 tok/s Prefill, TTFT 8.514 ms (3 Laufe)Qwen-AgentWorld-35B-A...Qwen3.6-35B-A3B - 103,2 tok/s Generation, 1.206 tok/s Prefill, TTFT 8.616 ms (3 Laufe)Qwen3.6-35B-A3BQwen3-VL-30B-A3B-Instruct - 102,2 tok/s Generation, 1.737 tok/s Prefill, TTFT 7.134 ms (3 Laufe)Qwen3-VL-30B-A3B-Inst...Meta-Llama-3.1-8B-Instruct - 83,4 tok/s Generation, 1.949 tok/s Prefill, TTFT 6.369 ms (3 Laufe)Meta-Llama-3.1-8B-Ins...Ministral-3-14B-Reasoning-2512 - 66,3 tok/s Generation, 1.123 tok/s Prefill, TTFT 10.027 ms (3 Laufe)Ministral-3-14B-Reaso...Seed-OSS-36B-Instruct - 43,0 tok/s Generation, 343 tok/s Prefill, TTFT 30.694 ms (3 Laufe)Seed-OSS-36B-InstructMagistral-Small-2509 - 37,6 tok/s Generation, 602 tok/s Prefill, TTFT 18.735 ms (3 Laufe)Magistral-Small-2509Qwen3.6-27B - 36,1 tok/s Generation, 432 tok/s Prefill, TTFT 24.072 ms (3 Laufe)Qwen3.6-27BMistral-Small-3.1-24B-Instruct-2503 - 31,3 tok/s Generation, 850 tok/s Prefill, TTFT 15.965 ms (3 Laufe)Mistral-Small-3.1-24B...Qwen2.5-32B-Instruct-AWQ - 22,6 tok/s Generation, 517 tok/s Prefill, TTFT 24.115 ms (3 Laufe)Qwen2.5-32B-Instruct-...OpenReasoning-Nemotron-32B - 21,1 tok/s Generation, 516 tok/s Prefill, TTFT 24.111 ms (3 Laufe)OpenReasoning-Nemotro...Qwen2.5-Coder-32B-Instruct - 20,6 tok/s Generation, 518 tok/s Prefill, TTFT 24.112 ms (3 Laufe)Qwen2.5-Coder-32B-Ins...Llama-3_3-Nemotron-Super-49B-v1_5 - 14,3 tok/s Generation, 306 tok/s Prefill, TTFT 40.454 ms (3 Laufe)Llama-3_3-Nemotron-Su...Nemotron-H-47B-Reasoning-128K - 10,7 tok/s Generation, 159 tok/s Prefill, TTFT 36.786 ms (2 Laufe)Nemotron-H-47B-Reason...Devstral-Small-2-24B-Instruct-2512 - 8,9 tok/s Generation, 22 tok/s Prefill, TTFT 906 ms (1 Lauf)Devstral-Small-2-24B-...
gpt-oss-20b 173,3 tok/sNorth-Mini-Code-1.0 131,9 tok/sQwen3-30B-A3B-Thinking-2507 131,2 tok/sGemma-4-26B-A4B-it 119,5 tok/sNVIDIA-Nemotron-3-Nano-30B-A3B 117,1 tok/sQwen3-Coder-30B-A3B-Instruct 115,8 tok/sNemotron-Cascade-2-30B-A3B 114,5 tok/sNVIDIA-Nemotron-3-Nano-4B 113,4 tok/sNemotron-3-Nano-Omni-30B-A3B-Reasoning 112,4 tok/sQwen3.5-35B-A3B 109,7 tok/sQwen3-30B-A3B-Instruct-2507 107,6 tok/sQwen-AgentWorld-35B-A3B 103,8 tok/sQwen3.6-35B-A3B 103,2 tok/sQwen3-VL-30B-A3B-Instruct 102,2 tok/sMeta-Llama-3.1-8B-Instruct 83,4 tok/sMinistral-3-14B-Reasoning-2512 66,3 tok/sSeed-OSS-36B-Instruct 43,0 tok/sMagistral-Small-2509 37,6 tok/sQwen3.6-27B 36,1 tok/sMistral-Small-3.1-24B-Instruct-2503 31,3 tok/sQwen2.5-32B-Instruct-AWQ 22,6 tok/sOpenReasoning-Nemotron-32B 21,1 tok/sQwen2.5-Coder-32B-Instruct 20,6 tok/sLlama-3_3-Nemotron-Super-49B-v1_5 14,3 tok/sNemotron-H-47B-Reasoning-128K 10,7 tok/sDevstral-Small-2-24B-Instruct-2512 8,9 tok/s

Getestete Modelle

Genutzte Betriebssysteme

← Alle Hardware