← Back to community benchmarks
gemma-4-E4B
Performance
1k
tokens
551.1
PP tok/s
34.0
TG tok/s
1858
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 551.1 | 34.0 | 4.5 GB | current |
| 4k | 618.8 | 32.7 | 4.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.0 | 1.00× |
| 2× | 63.7 | 1.87× |
| 4× | 81.6 | 2.40× |