← Back to community benchmarks
gemma-4-e4b-it
Performance
195k
tokens
2,951
PP tok/s
30.6
TG tok/s
67785
TTFT (ms)
12.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 4,945 | 128.1 | 5.6 GB | view |
| 128k | 3,803 | 40.9 | 9.9 GB | view |
| 195k | 2,951 | 30.6 | 12.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 128.1 | 1.00× |
| 2× | 230.1 | 1.80× |
| 4× | 347.3 | 2.71× |
| 8× | 642.0 | 5.01× |