← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
497.3
PP tok/s
48.6
TG tok/s
8237
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 457.0 | 51.9 | 14.2 GB | view |
| 4k | 497.3 | 48.6 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.9 | 1.00× |
| 2× | 68.3 | 1.32× |
| 4× | 81.4 | 1.57× |