← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
212.3
PP tok/s
15.0
TG tok/s
4823
TTFT (ms)
9.3
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 212.3 | 15.0 | 9.3 GB | current |
| 4k | 226.7 | 14.3 | 9.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.0 | 1.00× |
| 2× | 17.9 | 1.19× |
| 4× | 24.4 | 1.63× |