← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
212.6
PP tok/s
10.5
TG tok/s
19265
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.4
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 187.1 | 9.2 | 7.9 GB | view |
| 4k | 212.6 | 10.5 | 8.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.2 | 1.00× |
| 2× | 20.5 | 2.23× |
| 4× | 33.2 | 3.61× |