← Back to community benchmarks
gemma-4-e4b-it
Performance
8k
tokens
264.8
PP tok/s
17.2
TG tok/s
30942
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.0
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 251.7 | 22.2 | 4.5 GB | view |
| 4k | 280.2 | 21.4 | 4.6 GB | view |
| 8k | 264.8 | 17.2 | 4.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.2 | 1.00× |
| 2× | 19.3 | 0.87× |
| 4× | 11.9 | 0.54× |