Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Qwen (Alibaba)

Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30B

Benchmark profile and published results.

MoE30B
Position in the field

Best values compared

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

AMD Radeon AI PRO R9700All GPUs
Generation233,4 tok/s
Min 0,0Ø 235,6Max 2.491,2
Unter dem Durchschnitt · 4705 Systeme im Feld
Prefill7.121 tok/s
Min 4Ø 4.785Max 112.346
Ueber dem Durchschnitt · 4696 Systeme im Feld
Time to First Token750 ms
Min 20Ø 32.984Max 535.235
Ueber dem Durchschnitt · 4703 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

2622412212001794.1124.5615.0095.458Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 233,4 tok/s Generation, 5.057 tok/s Prefill, TTFT 2.646 ms (3 Laufe)AMD Radeon AI PRO R97...AMD Radeon RX 7900 XTX - 207,9 tok/s Generation, 4.513 tok/s Prefill, TTFT 2.485 ms (3 Laufe)AMD Radeon RX 7900 XTX
AMD Radeon AI PRO R9700 233,4 tok/sAMD Radeon RX 7900 XTX 207,9 tok/s

CPUby processor

2622412212001794.1124.5615.0095.458Prefill (tok/s)Generation (tok/s)AMD Ryzen 3 3100 4-Core Processor - 233,4 tok/s Generation, 5.057 tok/s Prefill, TTFT 2.646 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 207,9 tok/s Generation, 4.513 tok/s Prefill, TTFT 2.485 ms (3 Laufe)AMD Ryzen Threadrippe...
AMD Ryzen 3 3100 4-Core Processor 233,4 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 207,9 tok/s

ENGby engine

2572452332222104.4984.6894.8815.072Prefill (tok/s)Generation (tok/s)llama.cpp - 233,4 tok/s Generation, 4.785 tok/s Prefill, TTFT 2.566 ms (6 Laufe)llama.cpp
llama.cpp 233,4 tok/s
Throughput & latency

Performance benchmark

Metric:
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
233,40 tok/s TG
Prefill 7.121 · TTFT 4.462 ms
10×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
2Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,89 tok/s TG
Prefill 6.462 · TTFT 4.062 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
3Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
188,69 tok/s TG
Prefill 4.792 · TTFT 2.726 ms
5×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
4Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
157,77 tok/s TG
Prefill 4.563 · TTFT 2.532 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
5Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
94,91 tok/s TG
Prefill 3.258 · TTFT 750 ms
1×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
6Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
66,48 tok/s TG
Prefill 2.514 · TTFT 862 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 189 GB RAMllama.cppgodclawQ4_K_MDetails →
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.