← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
2,682
PP tok/s
126.1
TG tok/s
382
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,682 | 126.1 | 4.6 GB | current |
| 64k | 4,369 | 42.0 | 6.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 126.1 | 1.00× |
| 2× | 229.3 | 1.82× |
| 4× | 447.1 | 3.55× |
| 8× | 864.1 | 6.85× |