← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
202.2
PP tok/s
19.5
TG tok/s
5065
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.4
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 202.2 | 19.5 | 4.5 GB | current |
| 4k | 219.7 | 18.4 | 4.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.5 | 1.00× |
| 2× | 28.1 | 1.44× |
| 4× | 30.1 | 1.54× |