← Back to community benchmarks
gemma-4
Performance
4k
tokens
1,043
PP tok/s
33.8
TG tok/s
3927
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 860.4 | 36.7 | 14.7 GB | view |
| 4k | 1,043 | 33.8 | 15.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.7 | 1.00× |
| 2× | 55.0 | 1.50× |
| 4× | 68.3 | 1.86× |