← Back to community benchmarks
gemma-4-e2b-it
Performance
64k
tokens
2,052
PP tok/s
59.4
TG tok/s
31941
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,438 | 97.8 | 4.0 GB | view |
| 4k | 2,784 | 94.6 | 4.0 GB | view |
| 8k | 3,088 | 90.0 | 4.1 GB | view |
| 16k | 2,837 | 83.6 | 4.2 GB | view |
| 32k | 2,524 | 74.3 | 4.5 GB | view |
| 64k | 2,052 | 59.4 | 5.3 GB | current |
| 128k | 1,523 | 43.6 | 7.0 GB | view |
| 195k | 933.9 | 23.7 | 9.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.8 | 1.00× |
| 2× | 141.2 | 1.44× |
| 4× | 113.6 | 1.16× |
| 8× | 136.4 | 1.39× |