← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
617.1
PP tok/s
32.8
TG tok/s
6638
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 536.5 | 34.0 | 4.5 GB | view |
| 4k | 617.1 | 32.8 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.0 | 1.00× |
| 2× | 64.4 | 1.89× |
| 4× | 81.9 | 2.41× |