← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
465.8
PP tok/s
57.8
TG tok/s
2199
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 465.8 | 57.8 | 15.0 GB | current |
| 4k | 503.1 | 54.9 | 15.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.8 | 1.00× |
| 2× | 56.4 | 0.98× |
| 4× | 76.4 | 1.32× |