← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
490.8
PP tok/s
19.5
TG tok/s
2087
TTFT (ms)
7.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 490.8 | 19.5 | 7.9 GB | current |
| 4k | 543.5 | 19.2 | 8.0 GB | view |
| 8k | 540.4 | 18.6 | 8.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.5 | 1.00× |
| 2× | 37.5 | 1.92× |
| 4× | 56.6 | 2.90× |