← Back to community benchmarks
gemma-4-E4B-it
Performance
4k
tokens
587.9
PP tok/s
19.7
TG tok/s
6967
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 500.5 | 20.2 | 6.0 GB | view |
| 4k | 587.9 | 19.7 | 6.0 GB | current |
| 8k | 600.9 | 19.2 | 6.1 GB | view |
| 16k | 583.7 | 17.0 | 6.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.2 | 1.00× |
| 2× | 39.3 | 1.95× |
| 4× | 64.8 | 3.21× |