← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
1,229
PP tok/s
69.5
TG tok/s
834
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,229 | 69.5 | 14.3 GB | current |
| 4k | 1,720 | 66.3 | 14.9 GB | view |
| 8k | 1,802 | 60.5 | 15.1 GB | view |
| 16k | 1,738 | 55.2 | 15.6 GB | view |
| 32k | 1,512 | 46.4 | 16.0 GB | view |
| 64k | 941.4 | 28.6 | 17.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.5 | 1.00× |
| 2× | 75.9 | 1.09× |
| 4× | 88.8 | 1.28× |
| 8× | 104.7 | 1.51× |