← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
444.4
PP tok/s
40.3
TG tok/s
9217
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 401.2 | 43.7 | 4.6 GB | view |
| 4k | 444.4 | 40.3 | 4.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.7 | 1.00× |
| 2× | 52.8 | 1.21× |
| 4× | 55.6 | 1.27× |