Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DeepSeek

DeepSeek-V4-Flash290.9B

Benchmark profile and published results.

MoE290.9B
Position in the field

Best values compared

Best metrics of this model against the minimum, average and maximum of all published systems.

Generation20,6 tok/s
Min 0,0Ø 253,2Max 2.491,2
Unter dem Durchschnitt · 2823 Systeme im Feld
Prefill220 tok/s
Min 4Ø 3.470Max 39.029
Unter dem Durchschnitt · 2823 Systeme im Feld
Time to First Token16.976 ms
Min 20Ø 45.698Max 535.235
Ueber dem Durchschnitt · 2821 Systeme im Feld
Performance profile

Throughput by hardware & engine

Each bubble is a GPU, CPU or engine – position shows prompt processing (X) and output speed (Y), bubble size the number of runs.

GPUby graphics card

22,721,620,619,618,5157164170177Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 20,6 tok/s Generation, 167 tok/s Prefill, TTFT 65.962 ms (15 Laufe)AMD Radeon AI PRO R97...
AMD Radeon AI PRO R9700 20,6 tok/s

CPUby processor

22,721,620,619,618,5157164170177Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 20,6 tok/s Generation, 167 tok/s Prefill, TTFT 65.962 ms (15 Laufe)AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 20,6 tok/s

ENGby engine

22,721,620,619,618,5157164170177Prefill (tok/s)Generation (tok/s)llama.cpp - 20,6 tok/s Generation, 167 tok/s Prefill, TTFT 65.962 ms (15 Laufe)llama.cpp
llama.cpp 20,6 tok/s
Throughput & latency

Performance benchmark

Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
20,60 tok/s TG
Prefill 168 · TTFT 72.538 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
2DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
20,05 tok/s TG
Prefill 165 · TTFT 64.548 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
3DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
18,92 tok/s TG
Prefill 218 · TTFT 111.123 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
4DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
17,86 tok/s TG
Prefill 166 · TTFT 63.926 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
5DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
17,26 tok/s TG
Prefill 218 · TTFT 111.171 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
6DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
16,91 tok/s TG
Prefill 161 · TTFT 66.087 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
7DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,90 tok/s TG
Prefill 215 · TTFT 113.000 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
8DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
15,48 tok/s TG
Prefill 220 · TTFT 110.219 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
9DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
14,49 tok/s TG
Prefill 162 · TTFT 65.453 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
10DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,01 tok/s TG
Prefill 118 · TTFT 17.314 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
11DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,81 tok/s TG
Prefill 119 · TTFT 17.125 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
12DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,65 tok/s TG
Prefill 120 · TTFT 16.976 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
13DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,56 tok/s TG
Prefill 116 · TTFT 17.650 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
14DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
11,52 tok/s TG
Prefill 132 · TTFT 17.401 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
15DeepSeek-V4-Flash290.9BUD-Q4_K_XLDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
11,48 tok/s TG
Prefill 207 · TTFT 124.898 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclaw
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.