← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
668.0
PP tok/s
45.1
TG tok/s
1533
TTFT (ms)
25.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 668.0 | 45.1 | 25.8 GB | current |
| 4k | 726.4 | 42.9 | 26.4 GB | view |
| 8k | 723.6 | 42.1 | 26.6 GB | view |
| 32k | 584.9 | 36.4 | 27.8 GB | view |
| 64k | 482.9 | 29.4 | 30.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.1 | 1.00× |
| 2× | 66.4 | 1.47× |
| 4× | 82.6 | 1.83× |