Created bymario-alka.dePowered bynoob2claw.detricoma.de
Google

gemma-2-2b-it2B

Benchmark profile and published results.

Dense2B
Position in the field

Best values compared

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

Generation323,8 tok/s
Min 0,0Ø 245,7Max 3.484,3
Ueber dem Durchschnitt · 4971 Systeme im Feld
Prefill27.208 tok/s
Min 4Ø 4.892Max 112.346
Ueber dem Durchschnitt · 4953 Systeme im Feld
Time to First Token218 ms
Min 20Ø 31.420Max 535.235
Ueber dem Durchschnitt · 4968 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

4063042031010,004.8509.70114.551Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 323,8 tok/s Generation, 11.875 tok/s Prefill, TTFT 1.279 ms (6 Laufe)AMD Radeon RX 7900 XTXCPU-only - 75,1 tok/s Generation, 964 tok/s Prefill, TTFT 149.843 ms (5 Laufe)CPU-only
AMD Radeon RX 7900 XTX 323,8 tok/sCPU-only 75,1 tok/s

CPUby processor

4193152101050,007.79715.59423.391Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 323,8 tok/s Generation, 4.880 tok/s Prefill, TTFT 1.976 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 322,9 tok/s Generation, 18.870 tok/s Prefill, TTFT 583 ms (3 Laufe)AMD Ryzen Threadrippe...Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) - 75,1 tok/s Generation, 2.212 tok/s Prefill, TTFT 876 ms (1 Lauf)Apple M6 (unified CPU...Apple M6 (unified CPU/GPU SoC) - 68,1 tok/s Generation, 2.491 tok/s Prefill, TTFT 768 ms (1 Lauf)Apple M6 (unified CPU...4 x Cortex-A78C + 4 x Cortex-A55 - 7,9 tok/s Generation, 40 tok/s Prefill, TTFT 249.190 ms (3 Laufe)4 x Cortex-A78C + 4 x...
Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 323,8 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 322,9 tok/sApple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) 75,1 tok/sApple M6 (unified CPU/GPU SoC) 68,1 tok/s4 x Cortex-A78C + 4 x Cortex-A55 7,9 tok/s

ENGby engine

4073052041020,007.66715.33323.000Prefill (tok/s)Generation (tok/s)llama.cpp - 323,8 tok/s Generation, 2.460 tok/s Prefill, TTFT 125.583 ms (6 Laufe)llama.cppvLLM - 322,9 tok/s Generation, 18.870 tok/s Prefill, TTFT 583 ms (3 Laufe)vLLMlmstudio-mlx - 75,1 tok/s Generation, 2.212 tok/s Prefill, TTFT 876 ms (1 Lauf)lmstudio-mlxOllama - 68,1 tok/s Generation, 2.491 tok/s Prefill, TTFT 768 ms (1 Lauf)Ollama
llama.cpp 323,8 tok/svLLM 322,9 tok/slmstudio-mlx 75,1 tok/sOllama 68,1 tok/s
Throughput & latency

Performance benchmark

Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
323,81 tok/s TG
Prefill 6.071 · TTFT 3.506 ms
10×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
2gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
322,89 tok/s TG
Prefill 27.208 · TTFT 972 ms
10×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
3gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,46 tok/s TG
Prefill 5.449 · TTFT 1.783 ms
5×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
4gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
187,26 tok/s TG
Prefill 21.013 · TTFT 558 ms
5×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
5gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
110,95 tok/s TG
Prefill 3.119 · TTFT 639 ms
1×2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAMllama.cppgodclawQ4_K_M
6gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,08 tok/s TG
Prefill 2.212 · TTFT 876 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) · 24 GB RAMlmstudio-mlxlmstudioMLX 4bit
7gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
68,10 tok/s TG
Prefill 2.491 · TTFT 768 ms
1×Keine GPU (CPU-only)Apple M6 (unified CPU/GPU SoC) · 24 GB RAMOllamaopenclaw_cliQ4_0
8gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
37,77 tok/s TG
Prefill 8.388 · TTFT 218 ms
1×2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAMvLLMgodclaw
9gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,94 tok/s TG
Prefill 52 · TTFT 404.593 ms
10×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
10gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
7,49 tok/s TG
Prefill 35 · TTFT 283.919 ms
5×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
11gemma-2-2b-it2BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,76 tok/s TG
Prefill 31 · TTFT 59.057 ms
1×Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAMllama.cppopenclaw_cliQ4_K_M
Agent & chat rating

Harness benchmark

Noch keine Harnessbenchmarks fuer dieses Modell.