← Back to community benchmarks
gemma-4-e4b-it
Performance
16k
tokens
601.0
PP tok/s
16.8
TG tok/s
27262
TTFT (ms)
8.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 551.0 | 19.5 | 7.9 GB | view |
| 4k | 619.2 | 18.9 | 8.0 GB | view |
| 8k | 620.4 | 18.3 | 8.1 GB | view |
| 16k | 601.0 | 16.8 | 8.3 GB | current |
| 32k | 553.0 | 14.2 | 8.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.5 | 1.00× |
| 2× | 37.6 | 1.93× |
| 4× | 61.2 | 3.14× |