Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
st
Modellserver / Inferenz-Engine

strata

Alle Performance-Benchmarks, die mit diesem Modellserver gemessen wurden – Durchsatz, Prefill und Latenz.

20Benchmarks
1Modelle
Beste Generation
1.564,6 tok/s
Qwen3.8-Flash-Next
∅ Generation
364,7 tok/s
Schnitt aus 20 Läufen
Bester Prefill
2.600 tok/s
Prompt-Verarbeitung
Bester TTFT
1.128 ms
Time to First Token

Top-Modelle auf strata

Bester Durchsatz je Modell – umschaltbar nach Generation, Prefill oder Kombiwert.

Qwen3.8-Flash-Next180B
1.564,6 tok/s

Auf welcher Hardware laeuft strata am schnellsten?

Bester Durchsatz je Grafikkarte mit diesem Modellserver.

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
1.564,6 tok/s
NVIDIA GeForce RTX 3090
1.132,7 tok/s
NVIDIA GB10
492,8 tok/s
NVIDIA Tesla V100 PCIe 32GB
196,2 tok/s
Performanceprofil

Durchsatz mit strata

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

CPUnach Prozessor

1.9951.4969974990,03471.1271.9072.688Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 7945HX with Radeon Graphics - 1.564,6 tok/s Generation, 2.277 tok/s Prefill, TTFT 17.310 ms (3 Laufe)AMD Ryzen 9 7945HX wi...AMD Ryzen 5 5600X 6-Core Processor - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)AMD Ryzen 5 5600X 6-C...NVIDIA Grace - 492,8 tok/s Generation, 810 tok/s Prefill, TTFT 59.035 ms (6 Laufe)NVIDIA GraceAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics - 196,2 tok/s Generation, 757 tok/s Prefill, TTFT 36.737 ms (5 Laufe)AMD Ryzen 3 PRO 3200G...
AMD Ryzen 9 7945HX with Radeon Graphics 1.564,6 tok/sAMD Ryzen 5 5600X 6-Core Processor 1.132,7 tok/sNVIDIA Grace 492,8 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 196,2 tok/s

GPUnach Grafikkarte

1.9951.4969974990,03471.1271.9072.688Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.564,6 tok/s Generation, 2.277 tok/s Prefill, TTFT 17.310 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA GB10 (DGX Spark) - 492,8 tok/s Generation, 810 tok/s Prefill, TTFT 59.035 ms (6 Laufe)NVIDIA GB10 (DGX Spar...NVIDIA Tesla V100 PCIe 32GB - 196,2 tok/s Generation, 757 tok/s Prefill, TTFT 36.737 ms (5 Laufe)NVIDIA Tesla V100 PCI...
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.564,6 tok/sNVIDIA GeForce RTX 3090 1.132,7 tok/sNVIDIA GB10 (DGX Spark) 492,8 tok/sNVIDIA Tesla V100 PCIe 32GB 196,2 tok/s

MODnach Modell

1.7211.6431.5651.4861.4081.0011.0431.0861.128Prefill (tok/s)Generation (tok/s)Qwen3.8-Flash-Next - 1.564,6 tok/s Generation, 1.064 tok/s Prefill, TTFT 44.996 ms (20 Laufe)Qwen3.8-Flash-Next
Qwen3.8-Flash-Next 1.564,6 tok/s
Alle Messungen

20 Benchmark-Läufe

Jeder veroeffentlichte Lauf mit strata.

← Alle Engines
Messwert:
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.564,61 tok/s TG
Prefill 2.600 · TTFT 34.894 ms
10×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMstratagodclawUD-Q4_K_XL
2Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.132,67 tok/s TG
Prefill 1.930 · TTFT 47.978 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
3Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
783,55 tok/s TG
Prefill 2.459 · TTFT 15.907 ms
5×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMstratagodclawUD-Q4_K_XL
4Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
638,58 tok/s TG
Prefill 306 · TTFT 145.278 ms
10×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXS
5Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
572,23 tok/s TG
Prefill 1.826 · TTFT 21.491 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
6Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
492,83 tok/s TG
Prefill 1.231 · TTFT 103.873 ms
10×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawIQ3_XXS
7Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
420,20 tok/s TG
Prefill 656 · TTFT 131.641 ms
10×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawUD-IQ4_XS
8Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
319,40 tok/s TG
Prefill 254 · TTFT 73.516 ms
5×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXS
9Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
246,45 tok/s TG
Prefill 1.171 · TTFT 47.068 ms
5×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawIQ3_XXS
10Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
211,19 tok/s TG
Prefill 592 · TTFT 60.940 ms
5×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawUD-IQ4_XS
11Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
196,16 tok/s TG
Prefill 860 · TTFT 118.321 ms
10×NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAMstratagodclawIQ3_XXS
12Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
158,06 tok/s TG
Prefill 1.772 · TTFT 1.128 ms
1×NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAMstratagodclawUD-Q4_K_XL
13Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
137,92 tok/s TG
Prefill 818 · TTFT 45.184 ms
5×NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAMstratagodclawIQ3_XXS
14Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
116,39 tok/s TG
Prefill 1.389 · TTFT 1.421 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ2_XS
15Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
59,02 tok/s TG
Prefill 1.132 · TTFT 12.062 ms
5×NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAMstratagodclawIQ3_XXS
16Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
52,11 tok/s TG
Prefill 510 · TTFT 3.869 ms
1×NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAMstratagodclawIQ3_XXS
17Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
50,53 tok/s TG
Prefill 106 · TTFT 20.413 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMstratagodclawIQ3_XXS
18Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
49,88 tok/s TG
Prefill 909 · TTFT 2.194 ms
1×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawIQ3_XXS
19Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
49,60 tok/s TG
Prefill 468 · TTFT 4.250 ms
1×NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAMstratagodclawIQ3_XXS
20Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
41,83 tok/s TG
Prefill 301 · TTFT 8.495 ms
1×NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAMstratagodclawUD-IQ4_XS