← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
1,482
PP tok/s
41.1
TG tok/s
2764
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.7
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,337 | 42.7 | 7.3 GB | view |
| 4k | 1,482 | 41.1 | 7.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.7 | 1.00× |
| 2× | 61.1 | 1.43× |
| 4× | 84.1 | 1.97× |