← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
610.2
PP tok/s
56.3
TG tok/s
13425
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 565.0 | 65.7 | 14.2 GB | view |
| 4k | 606.1 | 62.8 | 14.7 GB | view |
| 8k | 610.2 | 56.3 | 14.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.7 | 1.00× |
| 2× | 87.2 | 1.33× |
| 4× | 99.6 | 1.52× |
| 8× | 114.5 | 1.74× |