← Back to community benchmarks
gemma-4-e4b-it
Performance
8k
tokens
938.6
PP tok/s
47.3
TG tok/s
8728
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 903.8 | 51.9 | 9.0 GB | view |
| 4k | 945.8 | 49.7 | 9.1 GB | view |
| 8k | 938.6 | 47.3 | 9.2 GB | current |
| 16k | 916.3 | 43.1 | 9.5 GB | view |
| 32k | 869.9 | 36.7 | 10.2 GB | view |
| 64k | 789.6 | 28.4 | 11.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.9 | 1.00× |
| 2× | 91.7 | 1.77× |
| 4× | 121.9 | 2.35× |
| 8× | 102.6 | 1.98× |