← Back to community benchmarks
gemma-4-12B-it
Performance
1k
tokens
146.8
PP tok/s
14.7
TG tok/s
6975
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.4.2.dev2
macOS
macOS 15.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 146.8 | 14.7 | 8.4 GB | current |
| 4k | 143.5 | 6.3 | 9.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.7 | 1.00× |
| 2× | 11.1 | 0.76× |
| 4× | 27.0 | 1.84× |