← Back to community benchmarks
gemma-4-e4b-it
Performance
16k
tokens
437.6
PP tok/s
27.3
TG tok/s
37438
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 387.0 | 42.8 | 4.6 GB | view |
| 4k | 439.0 | 37.8 | 4.7 GB | view |
| 8k | 450.7 | 32.9 | 4.8 GB | view |
| 16k | 437.6 | 27.3 | 4.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.8 | 1.00× |
| 2× | 51.9 | 1.21× |
| 4× | 58.1 | 1.36× |