Google

gemma-2-27b-it27B

Name: gemma-2-27b-it
Author: Google

Benchmark profile and published results.

Dense27B

Position in the field

Best values compared

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

Generation113,0 tok/s

Min 0,1Ø 159,1Max 717,6

Unter dem Durchschnitt · 361 Systeme im Feld

Prefill842 tok/s

Min 39Ø 5.819Max 52.503

Unter dem Durchschnitt · 361 Systeme im Feld

Time to First Token2.163 ms

Min 156Ø 18.353Max 354.928

Ueber dem Durchschnitt · 361 Systeme im Feld

Performance profile

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

AMD Radeon RX 7900 XTX 113,0 tok/s

Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 113,0 tok/s

llama.cpp 113,0 tok/s

Throughput & latency

Metric:

#	Model / Maker	Metrics	Parallel	GPU / CPU / RAM	Runtime
1	gemma-2-27b-it27BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	112,98 tok/s TG Prefill 330 · TTFT 60.679 ms	10×	2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM	llama.cppgodclawQ4_K_M	Details →
2	gemma-2-27b-it27BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	63,42 tok/s TG Prefill 674 · TTFT 30.833 ms	5×	2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM	llama.cppgodclawQ4_K_M	Details →
3	gemma-2-27b-it27BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)	31,94 tok/s TG Prefill 842 · TTFT 2.163 ms	1×	2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM	llama.cppgodclawQ4_K_M	Details →

Agent & chat rating

Noch keine Harnessbenchmarks fuer dieses Modell.