← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,666
PP tok/s
41.3
TG tok/s
2459
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.1
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,628 | 42.6 | 26.8 GB | view |
| 4k | 1,666 | 41.3 | 27.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.6 | 1.00× |
| 2× | 53.8 | 1.26× |
| 4× | 75.6 | 1.77× |