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

Qwen3-4B4B

Benchmark profile and published results.

Dense4B
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
Generation325,2 tok/s
Min 0,0Ø 77,4Max 667,0
Ueber dem Durchschnitt · 978 Systeme im Feld
Prefill9.520 tok/s
Min 4Ø 2.302Max 35.719
Ueber dem Durchschnitt · 978 Systeme im Feld
Time to First Token440 ms
Min 31Ø 57.832Max 535.235
Ueber dem Durchschnitt · 976 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

4233172111060,003.9707.94011.911Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 325,2 tok/s Generation, 7.193 tok/s Prefill, TTFT 1.751 ms (3 Laufe)AMD Radeon AI PRO R97...AMD Radeon RX 7900 XTX - 320,4 tok/s Generation, 9.607 tok/s Prefill, TTFT 1.584 ms (9 Laufe)AMD Radeon RX 7900 XTXAMD Oberon (PlayStation 5) - 101,5 tok/s Generation, 782 tok/s Prefill, TTFT 9.208 ms (2 Laufe)AMD Oberon (PlayStati...CPU-only - 1,3 tok/s Generation, 8 tok/s Prefill, TTFT 374.500 ms (3 Laufe)CPU-only
AMD Radeon AI PRO R9700 325,2 tok/sAMD Radeon RX 7900 XTX 320,4 tok/sAMD Oberon (PlayStation 5) 101,5 tok/sCPU-only 1,3 tok/s

CPUby processor

4233172111060,004.5349.06813.602Prefill (tok/s)Generation (tok/s)AMD Ryzen 3 3100 4-Core Processor - 325,2 tok/s Generation, 7.193 tok/s Prefill, TTFT 1.751 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 320,4 tok/s Generation, 10.970 tok/s Prefill, TTFT 1.493 ms (6 Laufe)AMD Ryzen Threadrippe...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 294,3 tok/s Generation, 6.880 tok/s Prefill, TTFT 1.765 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Zen2 8-Core (PlayStation 5) - 101,5 tok/s Generation, 782 tok/s Prefill, TTFT 9.208 ms (2 Laufe)AMD Zen2 8-Core (Play...AMD Jaguar 8-Core (PlayStation 4) - 1,3 tok/s Generation, 4 tok/s Prefill, TTFT 474.264 ms (1 Lauf)AMD Jaguar 8-Core (Pl...4 x Cortex-A78C + 4 x Cortex-A55 - 0,9 tok/s Generation, 11 tok/s Prefill, TTFT 324.617 ms (2 Laufe)4 x Cortex-A78C + 4 x...
AMD Ryzen 3 3100 4-Core Processor 325,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 320,4 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 294,3 tok/sAMD Zen2 8-Core (PlayStation 5) 101,5 tok/sAMD Jaguar 8-Core (PlayStation 4) 1,3 tok/s4 x Cortex-A78C + 4 x Cortex-A55 0,9 tok/s

ENGby engine

3593413233052872.3307.05911.78816.517Prefill (tok/s)Generation (tok/s)llama.cpp - 325,2 tok/s Generation, 4.826 tok/s Prefill, TTFT 82.646 ms (14 Laufe)llama.cppvLLM - 320,4 tok/s Generation, 14.021 tok/s Prefill, TTFT 1.458 ms (3 Laufe)vLLM
llama.cpp 325,2 tok/svLLM 320,4 tok/s
Throughput & latency

Performance benchmark

Metric:
GPUs
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
325,24 tok/s TG
Prefill 9.520 · TTFT 2.933 ms
10×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ8_0Details →
2Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
320,40 tok/s TG
Prefill 19.188 · TTFT 3.026 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
3Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
305,48 tok/s TG
Prefill 10.848 · TTFT 2.513 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
4Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
294,28 tok/s TG
Prefill 9.688 · TTFT 2.856 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
5Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
221,06 tok/s TG
Prefill 15.907 · TTFT 999 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
6Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,67 tok/s TG
Prefill 6.514 · TTFT 1.882 ms
5×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ8_0Details →
7Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
211,36 tok/s TG
Prefill 8.014 · TTFT 1.554 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
8Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
184,99 tok/s TG
Prefill 7.151 · TTFT 1.754 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
9Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
101,48 tok/s TG
Prefill 945 · TTFT 14.455 ms
5×AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAMllama.cppgodclawQ4_K_MDetails →
10Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
96,67 tok/s TG
Prefill 3.801 · TTFT 687 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_MDetails →
11Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
92,71 tok/s TG
Prefill 620 · TTFT 3.961 ms
1×AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAMllama.cppgodclawQ4_K_MDetails →
12Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
92,16 tok/s TG
Prefill 4.895 · TTFT 521 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMllama.cppgodclawQ4_K_MDetails →
13Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
85,07 tok/s TG
Prefill 5.545 · TTFT 440 ms
1×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ8_0Details →
14Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
47,44 tok/s TG
Prefill 6.967 · TTFT 349 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclawDetails →
15Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1,25 tok/s TG
Prefill 4 · TTFT 474.264 ms
1×Keine GPU (CPU-only)AMD Jaguar 8-Core (PlayStation 4) · 5 GB RAMllama.cppgodclawQ4_K_MDetails →
16Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,91 tok/s TG
Prefill 15 · TTFT 142.282 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
17Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
0,01 tok/s TG
Prefill 6 · TTFT 506.953 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_MDetails →
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.