← Back to community benchmarks
gemma-4-E4B-it
Performance
4k
tokens
1,701
PP tok/s
27.1
TG tok/s
2408
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,294 | 27.3 | 6.0 GB | view |
| 4k | 1,701 | 27.1 | 6.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.3 | 1.00× |
| 2× | 56.8 | 2.08× |
| 4× | 112.3 | 4.11× |