← Back to community benchmarks
gemma-4-e2b-it
Performance
1k
tokens
580.0
PP tok/s
36.3
TG tok/s
1765
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
8 GB
GPU Cores
8
Software
oMLX
v0.3.7rc1
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 580.0 | 36.3 | 2.9 GB | current |
| 4k | 742.6 | 34.2 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.3 | 1.00× |
| 2× | 52.0 | 1.43× |
| 4× | 56.0 | 1.54× |