← Back to community benchmarks
gemma-4-26B-A4B-it-qat
Performance
1k
tokens
1,332
PP tok/s
73.0
TG tok/s
769
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,332 | 73.0 | 14.3 GB | current |
| 4k | 1,795 | 72.9 | 14.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.0 | 1.00× |
| 2× | 100.8 | 1.38× |
| 4× | 131.6 | 1.80× |
| 8× | 124.1 | 1.70× |