← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
309.4
PP tok/s
25.3
TG tok/s
13238
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 279.6 | 26.1 | 4.5 GB | view |
| 4k | 309.4 | 25.3 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.1 | 1.00× |
| 2× | 37.7 | 1.44× |
| 4× | 40.1 | 1.54× |