← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
352.7
PP tok/s
39.4
TG tok/s
2903
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 352.7 | 39.4 | 4.6 GB | current |
| 4k | 397.5 | 36.9 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.4 | 1.00× |
| 2× | 46.7 | 1.19× |
| 4× | 51.2 | 1.30× |