← Back to community benchmarks
gemma-4-e4b-it
Performance
16k
tokens
205.9
PP tok/s
7.0
TG tok/s
79564
TTFT (ms)
9.3
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 500.7 | 15.5 | 8.8 GB | view |
| 4k | 519.8 | 15.6 | 8.9 GB | view |
| 8k | 491.6 | 15.2 | 9.1 GB | view |
| 16k | 205.9 | 7.0 | 9.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.5 | 1.00× |
| 2× | 21.2 | 1.37× |
| 4× | 42.0 | 2.71× |