← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
248.4
PP tok/s
19.3
TG tok/s
16488
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M2 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.6
macOS
macOS 15.6.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 233.5 | 20.0 | 6.2 GB | view |
| 4k | 248.4 | 19.3 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.0 | 1.00× |
| 2× | 23.9 | 1.19× |
| 4× | 25.5 | 1.27× |