← Back to community benchmarks
Gemma-4-E4B-IT
Performance
1k
tokens
440.9
PP tok/s
49.3
TG tok/s
2323
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 440.9 | 49.3 | 4.6 GB | current |
| 4k | 492.2 | 46.1 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 59.2 | 1.20× |
| 4× | 64.6 | 1.31× |