← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
1,566
PP tok/s
113.3
TG tok/s
654
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,566 | 113.3 | 14.3 GB | current |
| 4k | 3,132 | 110.4 | 14.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 113.3 | 1.00× |
| 2× | 171.3 | 1.51× |
| 4× | 233.7 | 2.06× |