← Back to community benchmarks
gemma-4-e2b
Performance
1k
tokens
1,073
PP tok/s
82.3
TG tok/s
955
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
32 GB
GPU Cores
19
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,073 | 82.3 | 3.2 GB | current |
| 4k | 1,614 | 76.0 | 3.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.3 | 1.00× |
| 2× | 99.6 | 1.21× |
| 4× | 109.0 | 1.32× |