← Back to community benchmarks
gemma-4-E4B-it
Performance
4k
tokens
1,538
PP tok/s
60.0
TG tok/s
2663
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,547 | 62.1 | 7.5 GB | view |
| 4k | 1,538 | 60.0 | 7.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.1 | 1.00× |
| 2× | 119.1 | 1.92× |
| 4× | 164.1 | 2.64× |