← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
2,584
PP tok/s
107.8
TG tok/s
1585
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
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 | 2,224 | 114.8 | 14.2 GB | view |
| 4k | 2,584 | 107.8 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 114.8 | 1.00× |
| 2× | 170.5 | 1.49× |
| 4× | 231.7 | 2.02× |
| 8× | 282.5 | 2.46× |