← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
861.1
PP tok/s
43.1
TG tok/s
4757
TTFT (ms)
9.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
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 | 871.3 | 47.1 | 9.0 GB | view |
| 4k | 861.1 | 43.1 | 9.1 GB | current |
| 8k | 757.5 | 40.1 | 9.2 GB | view |
| 16k | 759.4 | 37.5 | 9.5 GB | view |
| 32k | 690.5 | 30.6 | 10.2 GB | view |
| 64k | 629.2 | 21.1 | 10.5 GB | view |
| 128k | 512.3 | 13.7 | 12.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.1 | 1.00× |
| 2× | 66.5 | 1.41× |
| 4× | 76.8 | 1.63× |