gemma-4-E2B-it
38 records across 8 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 473.7 | 6115.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 326.4 | 8830.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 255.2 | 2642.0 | – | – | 1024 | 2026-10-13 | community | – | source |
| M6 | gemma-4-E2B-it | oQ4e | oMLX | 244.9 | 4200.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 234.3 | 8370.0 | – | – | 8192 | 2026-10-15 | community | – | source |
| M6 | gemma-4-E2B-it | oQ4e | oMLX | 229.0 | 7256.0 | – | – | 16384 | 2026-10-16 | community | – | source |
| M6 | gemma-4-E2B-it | oQ4e | oMLX | 224.7 | 7866.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 210.1 | 8376.0 | – | – | 8192 | 2026-10-15 | community | contradiction | source |
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 203.3 | 8227.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M3 Ultra | gemma-4-E2B-it | oQ4e | oMLX | 188.3 | 8220.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 185.7 | 4022.0 | – | – | 1024 | 2026-10-13 | community | contradiction | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 156.2 | 5897.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 149.3 | 5519.0 | – | – | 8192 | 2026-10-13 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 145.8 | 4034.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| M6 | gemma-4-E2B-it | oQ4e | oMLX | 143.7 | 6511.0 | – | – | 16384 | 2026-10-16 | community | contradiction | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 131.2 | 4109.0 | – | – | 1024 | 2026-10-15 | community | contradiction | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 127.0 | 4132.0 | – | – | 1024 | 2026-10-15 | community | contradiction | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 108.1 | 4915.0 | – | – | 16384 | 2026-10-13 | community | – | source |
| M1 | gemma-4-E2B-it | oQ4e | oMLX | 80.3 | 955.5 | – | – | 1024 | 2026-10-15 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 75.6 | 4354.0 | – | – | 1024 | 2026-10-15 | community | contradiction | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 75.2 | 4180.0 | – | – | 1024 | 2026-10-15 | community | contradiction | source |
| M1 | gemma-4-E2B-it | oQ4e | oMLX | 70.5 | 972.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M1 Pro | gemma-4-E2B-it | oQ3 | oMLX | 66.0 | 1839.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M4 | gemma-4-E2B-it | 4bit | oMLX | 64.4 | 2270.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 | gemma-4-E2B-it | oQ4e | oMLX | 53.2 | 4619.0 | – | – | 32768 | 2026-10-13 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 51.1 | 1168.0 | – | – | 4096 | 2026-10-10 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 49.3 | 1150.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M4 | gemma-4-E2B-it | OptiQ-4bit | oMLX | 46.2 | 2272.0 | – | – | 1024 | 2026-10-14 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 45.9 | 1162.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M4 | gemma-4-E2B-it | OptiQ-4bit | oMLX | 45.5 | 2315.0 | – | – | 4096 | 2026-10-14 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 44.8 | 1137.0 | – | – | 8192 | 2026-10-10 | community | – | source |
| M1 Max | gemma-4-E2B-it | oQ4e | oMLX | 39.1 | 869.4 | – | – | 4096 | 2026-10-13 | community | – | source |
| M4 | gemma-4-E2B-it | 8bit | oMLX | 39.1 | 2260.0 | – | – | 1024 | 2026-10-17 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 38.5 | 1057.0 | – | – | 16384 | 2026-10-10 | community | – | source |
| M4 | gemma-4-E2B-it | 8bit | oMLX | 35.7 | 2352.0 | – | – | 4096 | 2026-10-17 | community | – | source |
| M1 Max | gemma-4-E2B-it | oQ4e | oMLX | 31.0 | 1198.0 | – | – | 16384 | 2026-10-13 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 22.2 | 596.5 | – | – | 65536 | 2026-10-10 | community | – | source |
| M2 | gemma-4-E2B-it | oQ4e | oMLX | 21.6 | 751.5 | – | – | 32768 | 2026-10-10 | community | – | source |