← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
472.6
PP tok/s
48.2
TG tok/s
8667
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
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 | 432.6 | 53.6 | 14.2 GB | view |
| 4k | 472.6 | 48.2 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.6 | 1.00× |
| 2× | 69.4 | 1.29× |
| 4× | 80.6 | 1.50× |