G
Manufacturer
Google
Gemma-Modellfamilie von Google DeepMind.
Best token generation
2.491,2 tok/s
gemma-4-E2B-it
Best prefill
55.259,6 tok/s
gemma-4-E2B-it
∅ Token generation
328,8 tok/s
Average of 442 runs
∅ Prefill
6.040,3 tok/s
Average of 442 runs
Best TTFT
91 ms
gemma4:31b
Best harness rate
91%
Gemma-4-26B-A4B-it
🏆
gemma-4-E2B-it · fastest model at 2.491,2 tok/s token generation
Best prefill of this manufacturer: 55.259,6 tok/s (gemma-4-E2B-it)
Best prefill of this manufacturer: 55.259,6 tok/s (gemma-4-E2B-it)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.
Models
All benchmarks →16 assigned
gemma-2-27b-it27B3 runs
69,4tok/s Ø
Min 31,9Max 113,0
gemma-2-2b-it2B11 runs
123,4tok/s Ø
Min 3,8Max 323,8
gemma-2-9b-it9B5 runs
76,4tok/s Ø
Min 20,3Max 171,6
gemma-3n-E4B-it8B11 runs
140,0tok/s Ø
Min 39,4Max 273,1
gemma-4-12B-it12B104 runs
260,7tok/s Ø
Min 22,3Max 1.104,3
gemma-4-12B-it-assistant12B0 runs
No performance data yet
Gemma-4-26B-A4B26B7 runs
155,4tok/s Ø
Min 47,1Max 264,1
Gemma-4-26B-A4B-it26B94 runs
384,6tok/s Ø
Min 32,4Max 1.604,6
gemma-4-26B-A4B-it-assistant26B3 runs
58,3tok/s Ø
Min 33,0Max 74,5
gemma-4-31B-it31B40 runs
89,6tok/s Ø
Min 16,8Max 251,1
gemma-4-31B-it-assistant31B0 runs
No performance data yet
gemma-4-E2B-it5B100 runs
506,5tok/s Ø
Min 6,8Max 2.491,2
gemma-4-E2B-it-assistant5B0 runs
No performance data yet
gemma-4-E4B-it8B57 runs
440,9tok/s Ø
Min 37,9Max 1.758,6
gemma-4-E4B-it-assistant8B0 runs
No performance data yet
gemma4:31b31B15 runs
47,3tok/s Ø
Min 10,5Max 174,1

