← Back to community benchmarks
gemma-4-26b-a4b
Performance
32k
tokens
3,105
PP tok/s
12.6
TG tok/s
10553
TTFT (ms)
22.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.1
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,365 | 20.6 | 20.9 GB | view |
| 4k | 3,642 | 63.8 | 21.4 GB | view |
| 8k | 3,670 | 26.2 | 21.5 GB | view |
| 16k | 3,529 | 16.9 | 21.9 GB | view |
| 32k | 3,105 | 12.6 | 22.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.6 | 1.00× |
| 2× | 44.2 | 2.15× |
| 4× | 76.4 | 3.71× |