← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
369.9
PP tok/s
29.1
TG tok/s
11072
TTFT (ms)
14.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 365.8 | 34.0 | 14.2 GB | view |
| 4k | 369.9 | 29.1 | 14.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.0 | 1.00× |
| 2× | 50.1 | 1.47× |
| 4× | 57.8 | 1.70× |