← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
3,487
PP tok/s
75.7
TG tok/s
1175
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,995 | 81.5 | 4.6 GB | view |
| 4k | 3,487 | 75.7 | 4.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.5 | 1.00× |
| 2× | 146.8 | 1.80× |
| 4× | 205.0 | 2.52× |