← Back to community benchmarks
gemma-4-e2b-it
Performance
1k
tokens
1,548
PP tok/s
62.5
TG tok/s
662
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,548 | 62.5 | 3.8 GB | current |
| 4k | 1,658 | 57.0 | 3.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.5 | 1.00× |
| 2× | 105.0 | 1.68× |
| 4× | 146.0 | 2.34× |